© 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. 12-LLAMASCOPE-RES-32K
    11. 24677
    Prev
    Next
    INDEX
    Explanations

    different categories and subjects related to various topics of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dG
    -0.14
    eson
    -0.14
    nist
    -0.14
    undra
    -0.14
    eos
    -0.14
    inci
    -0.14
    елик
    -0.14
    rai
    -0.14
     ä¹
    -0.13
    جÙĪÛĮ
    -0.13
    POSITIVE LOGITS
    \Id
    0.15
    802
    0.15
    ÐĽÐ¬
    0.15
     Affero
    0.14
     edge
    0.14
    827
    0.13
    defgroup
    0.13
    Ps
    0.13
     slik
    0.13
     estates
    0.13
    Activations Density 0.043%

    No Known Activations