© 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. 126813
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a potential or ability to perform tasks or actions

    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
    dea
    -0.08
    propertyName
    -0.08
    fon
    -0.08
    ghi
    -0.07
    ÙĨØ´
    -0.07
    _COMPILE
    -0.07
    -webpack
    -0.07
    anic
    -0.07
    urban
    -0.07
    zee
    -0.07
    POSITIVE LOGITS
    -bodied
    0.08
    (cap
    0.07
    theid
    0.07
    959
    0.06
     of
    0.06
    ioned
    0.06
    ippet
    0.06
    481
    0.06
    ÑĨиÑĤ
    0.06
     latter
    0.06
    Activations Density 0.006%

    No Known Activations