© 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. 939
    Prev
    Next
    INDEX
    Explanations

    articles and determiners that precede key concepts or variables in discussions about healthcare and legal situations

    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
    eling
    -0.06
    az
    -0.06
     setC
    -0.06
    .tbl
    -0.06
    aminer
    -0.06
    RefreshLayout
    -0.06
     mis
    -0.05
    erc
    -0.05
     ins
    -0.05
    uth
    -0.05
    POSITIVE LOGITS
    rotch
    0.08
    \Catalog
    0.07
     gerçekten
    0.07
    abel
    0.07
     algun
    0.07
    ildo
    0.07
    ullan
    0.06
    -License
    0.06
    äll
    0.06
     nÃło
    0.06
    Activations Density 0.030%

    No Known Activations