© 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. 9-LLAMASCOPE-RES-131K
    11. 95785
    Prev
    Next
    INDEX
    Explanations

    references to organizational projects and initiatives

    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
    essel
    -0.07
    chop
    -0.07
    ìľĦìĽIJ
    -0.07
     Commissioner
    -0.07
    pawn
    -0.06
    .Logf
    -0.06
     commissioner
    -0.06
    ork
    -0.06
    绾
    -0.06
    FontOfSize
    -0.06
    POSITIVE LOGITS
    кÑĥл
    0.07
    åī¯
    0.07
    oids
    0.06
    ær
    0.06
    urum
    0.06
     Eig
    0.06
     personalize
    0.06
    STIT
    0.06
    STA
    0.06
    gle
    0.06
    Activations Density 0.497%

    No Known Activations