© 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. 61239
    Prev
    Next
    INDEX
    Explanations

    locational keywords and references to local communities

    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
     /
    -0.06
     ("
    -0.06
     (
    -0.06
     "
    -0.06
    S
    -0.06
     Underground
    -0.06
    API
    -0.06
     ('
    -0.06
    awe
    -0.05
    502
    -0.05
    POSITIVE LOGITS
     lượt
    0.07
     ÙħÛĮÙĦادÛĮ
    0.07
    ROID
    0.07
    abase
    0.07
     dopl
    0.07
    lý
    0.07
    iming
    0.07
     vids
    0.07
    ispecies
    0.07
    ë²
    0.07
    Activations Density 0.000%

    No Known Activations