© 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. 17-LLAMASCOPE-RES-131K
    11. 95422
    Prev
    Next
    INDEX
    Explanations

    numerical values and punctuation

    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
    ÑĢап
    -0.07
    .VisualBasic
    -0.07
     indeb
    -0.06
     Dop
    -0.06
    quip
    -0.06
    ãĥ¬ãĥĵ
    -0.06
     ga
    -0.06
    .Apis
    -0.06
     Go
    -0.06
     PROCUREMENT
    -0.06
    POSITIVE LOGITS
    ivers
    0.07
    olv
    0.07
    ijd
    0.07
    á»ĭ
    0.07
    igkeit
    0.07
    azel
    0.06
    ondere
    0.06
    KO
    0.06
    NoArgsConstructor
    0.06
    PLY
    0.06
    Activations Density 0.001%

    No Known Activations