© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94565
    Prev
    Next
    INDEX
    Explanations

    citation and reference formatting elements

    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
    pon
    -0.06
    oster
    -0.06
    nell
    -0.06
    isel
    -0.05
     Silver
    -0.05
    with
    -0.05
    iske
    -0.05
     bent
    -0.05
     Sherman
    -0.05
    iler
    -0.05
    POSITIVE LOGITS
    ÅĻes
    0.08
    .annot
    0.08
     PROP
    0.07
    zik
    0.07
    leigh
    0.07
    SWG
    0.07
    .Restr
    0.07
    боÑĤ
    0.07
    oose
    0.07
    ÎŃλ
    0.07
    Activations Density 0.010%

    No Known Activations