© 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. 93209
    Prev
    Next
    INDEX
    Explanations

    references to various topics

    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
     Hicks
    -0.06
     Klein
    -0.06
    á»ī
    -0.06
    ivate
    -0.06
    arm
    -0.06
    ihan
    -0.06
    ias
    -0.06
    irus
    -0.06
    lets
    -0.06
    ps
    -0.05
    POSITIVE LOGITS
     anybody
    0.08
     anything
    0.08
    sÃŃ
    0.08
    anything
    0.07
    /all
    0.07
    _ros
    0.07
     qualquer
    0.07
     anyone
    0.07
    everything
    0.07
    tura
    0.07
    Activations Density 0.004%

    No Known Activations