© 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. 15-LLAMASCOPE-RES-131K
    11. 89955
    Prev
    Next
    INDEX
    Explanations

    names of countries and regions

    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
    Ñĩин
    -0.08
    nde
    -0.07
    erde
    -0.07
    renc
    -0.07
    izon
    -0.07
    mps
    -0.07
    à¸į
    -0.07
    Utf
    -0.07
    CRET
    -0.07
    aset
    -0.07
    POSITIVE LOGITS
     Danielle
    0.06
     Fri
    0.05
    _tA
    0.05
    _tD
    0.05
    899
    0.05
    729
    0.05
     Jury
    0.05
    ãģ¡ãģ¯
    0.05
    ár
    0.05
     fug
    0.05
    Activations Density 0.025%

    No Known Activations