© 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 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. 17-LLAMASCOPE-RES-131K
    11. 84259
    Prev
    Next
    INDEX
    Explanations

    keywords related to database genres or classifications

    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
    eyen
    -0.08
     kvin
    -0.07
    績
    -0.07
    ValuePair
    -0.07
    gang
    -0.07
    ÅĻ
    -0.07
    .Undef
    -0.07
    inkle
    -0.07
    esine
    -0.07
    ancellor
    -0.06
    POSITIVE LOGITS
     mains
    0.06
     Lamp
    0.06
     Moose
    0.06
     non
    0.06
    .sel
    0.06
    anship
    0.06
    -non
    0.06
     temporal
    0.05
     uniqueness
    0.05
    ower
    0.05
    Activations Density 0.000%

    No Known Activations