© 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. 9-LLAMASCOPE-RES-131K
    11. 94440
    Prev
    Next
    INDEX
    Explanations

    names of musical acts or groups

    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
    Writes
    -0.07
    /apps
    -0.07
     ZákladnÃŃ
    -0.07
    gba
    -0.07
    Ø´Ùħ
    -0.06
    iska
    -0.06
    .Interop
    -0.06
    ç´
    -0.06
    aura
    -0.06
     Bilim
    -0.06
    POSITIVE LOGITS
     duo
    0.08
     tandem
    0.06
    -du
    0.06
    994
    0.06
     halves
    0.06
     personalities
    0.06
     Duo
    0.06
     twin
    0.05
     sist
    0.05
    AA
    0.05
    Activations Density 0.036%

    No Known Activations