© 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. 74004
    Prev
    Next
    INDEX
    Explanations

    terms and references related to lineage or ancestry

    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
    antas
    -0.07
    rella
    -0.07
    StringRef
    -0.07
    ÌĨ
    -0.07
    ulong
    -0.07
    碼
    -0.07
    ToBounds
    -0.07
    /copyleft
    -0.07
    Æ°á»Ľ
    -0.07
    .scalablytyped
    -0.07
    POSITIVE LOGITS
     gene
    0.09
     family
    0.08
     count
    0.06
    å§ĵ
    0.06
    br
    0.06
     surname
    0.06
     Gene
    0.06
     Family
    0.06
     Counts
    0.06
    ç³»
    0.06
    Activations Density 0.002%

    No Known Activations