© 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. 42136
    Prev
    Next
    INDEX
    Explanations

    concepts related to genetics and evolutionary biology

    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
     sold
    -0.06
    phen
    -0.06
     cer
    -0.06
    286
    -0.06
     fet
    -0.06
     Paladin
    -0.06
    raž
    -0.05
     bald
    -0.05
     reckon
    -0.05
     Clip
    -0.05
    POSITIVE LOGITS
    tog
    0.07
    orton
    0.07
    LOSS
    0.07
    å°ļ
    0.07
     Riding
    0.06
    ünkü
    0.06
    .Modules
    0.06
    _$_
    0.06
    WEEN
    0.06
    ANI
    0.06
    Activations Density 0.015%

    No Known Activations