© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 95600
    Prev
    Next
    INDEX
    Explanations

    terms related to Android programming and user interface components

    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
    zion
    -0.08
    ssi
    -0.08
    venes
    -0.07
    heet
    -0.07
    ek
    -0.07
    edii
    -0.07
    _customize
    -0.07
    èī
    -0.07
    ppy
    -0.07
    doch
    -0.07
    POSITIVE LOGITS
    /of
    0.06
    ιÏĥÏĦο
    0.05
    rello
    0.05
     pos
    0.05
     Katz
    0.05
     ted
    0.05
    E
    0.05
     Natal
    0.05
    ç«ĭ
    0.05
     Fle
    0.05
    Activations Density 0.001%

    No Known Activations