© 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. 56092
    Prev
    Next
    INDEX
    Explanations

    boolean conditions and their states

    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
    ÑŁ
    -0.08
    uell
    -0.07
    ););↵
    -0.07
    εια
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.06
    vely
    -0.06
    ÑĢел
    -0.06
    dispose
    -0.06
    ÏĦÏģο
    -0.06
    isku
    -0.06
    POSITIVE LOGITS
    pars
    0.06
    iana
    0.06
    avig
    0.06
    acons
    0.06
    Ïİν
    0.06
    ild
    0.06
    μι
    0.06
    l
    0.06
    .shtml
    0.06
    ilden
    0.06
    Activations Density 0.022%

    No Known Activations