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

    Neuronpedia

    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. 4-LLAMASCOPE-RES-32K
    11. 30103
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of automotive-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atform
    -0.18
    živ
    -0.15
    irsch
    -0.15
    raman
    -0.15
    arto
    -0.14
    Ñıн
    -0.14
    /Set
    -0.14
    ust
    -0.14
    erland
    -0.14
    ystate
    -0.14
    POSITIVE LOGITS
    imum
    0.18
    ãĥķãĤ
    0.17
    thumbnail
    0.15
    ograd
    0.15
    plied
    0.15
     Lawn
    0.15
    mlin
    0.15
    ãĥ³ãĤ°
    0.15
    inz
    0.14
    inject
    0.14
    Activations Density 0.003%

    No Known Activations