© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 10633
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    word fragments that are part of proper nouns, particularly place names and personal names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tual
    -0.22
    leton
    -0.20
    ty
    -0.19
    gro
    -0.19
    ë¡ľ
    -0.19
    ted
    -0.18
    ÙħاÙĨÛĮ
    -0.18
    letic
    -0.17
    umann
    -0.17
    erson
    -0.17
    POSITIVE LOGITS
    ymous
    0.26
    neau
    0.23
    etwork
    0.23
    ned
    0.23
    ettes
    0.21
    nection
    0.21
    naire
    0.21
     thù
    0.20
    ormal
    0.20
    ne
    0.20
    Activations Density 0.303%

    No Known Activations