© 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. 61808
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics or numerical data

    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
    .bunifuFlatButton
    -0.07
    InputDialog
    -0.07
    alue
    -0.07
    istique
    -0.07
    okino
    -0.07
    omitempty
    -0.07
    ¼åIJĪ
    -0.07
    Ñīин
    -0.07
    uilt
    -0.06
    illac
    -0.06
    POSITIVE LOGITS
     number
    0.08
     who
    0.07
    ahlen
    0.07
     people
    0.07
     meisten
    0.06
     éģ
    0.06
    number
    0.06
     whose
    0.06
     row
    0.06
     fewer
    0.06
    Activations Density 0.019%

    No Known Activations