© 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. 17768
    Prev
    Next
    INDEX
    Explanations

    mentions of colors

    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
    asso
    -0.06
    owers
    -0.06
    ego
    -0.06
    âĢª
    -0.06
    o
    -0.05
    ġ
    -0.05
    :update
    -0.05
    233
    -0.05
    i
    -0.05
    egis
    -0.05
    POSITIVE LOGITS
    Äł
    0.08
     NONINFRINGEMENT
    0.08
    ãģ°ãģĭãĤĬ
    0.07
    sed
    0.07
    inue
    0.07
    rafted
    0.07
    aleigh
    0.07
    sian
    0.07
    ahlen
    0.07
    ilim
    0.07
    Activations Density 0.045%

    No Known Activations