© 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. 17-LLAMASCOPE-RES-131K
    11. 118809
    Prev
    Next
    INDEX
    Explanations

    references to audio and visual materials, such as films and recordings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (s
    -0.10
    (es
    -0.08
    [s
    -0.08
    amientos
    -0.07
    cher
    -0.07
    cott
    -0.06
    so
    -0.06
    cio
    -0.06
     Sherman
    -0.06
    sWith
    -0.06
    POSITIVE LOGITS
    ">//
    0.07
    NetMessage
    0.07
    ëŁī
    0.07
    nea
    0.06
    ubat
    0.06
    .bunifuFlatButton
    0.06
    ipt
    0.06
    773
    0.06
    DK
    0.06
    igar
    0.06
    Activations Density 0.585%

    No Known Activations