© 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. 17-LLAMASCOPE-RES-131K
    11. 84683
    Prev
    Next
    INDEX
    Explanations

    formatting elements and symbols in text

    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
    .LA
    -0.07
    NX
    -0.07
    .Reporting
    -0.06
    igue
    -0.06
    igid
    -0.06
    vely
    -0.06
    lical
    -0.06
     struk
    -0.06
    Ā
    -0.06
    ιν
    -0.06
    POSITIVE LOGITS
    edBy
    0.07
    Hat
    0.07
    odos
    0.07
     Hat
    0.06
     Miscellaneous
    0.06
     vivastreet
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
     ragaz
    0.06
    orsi
    0.06
    Ñĩай
    0.06
    Activations Density 0.007%

    No Known Activations