© 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. 41487
    Prev
    Next
    INDEX
    Explanations

    the keyword "main" and its variations or related terms in coding and documentation contexts

    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
    auga
    -0.07
    ÑĢемÑı
    -0.07
    ãĤ¶ãĥ¼
    -0.07
     çĻº
    -0.07
    üh
    -0.07
    на
    -0.06
    ÑĩÑĥ
    -0.06
    gorm
    -0.06
    osg
    -0.06
    _By
    -0.06
    POSITIVE LOGITS
    edn
    0.07
    StackSize
    0.06
    ilden
    0.06
    869
    0.06
     Antony
    0.06
    819
    0.06
     polar
    0.05
    ymph
    0.05
    rike
    0.05
    论åĿĽ
    0.05
    Activations Density 0.001%

    No Known Activations