© 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. 129102
    Prev
    Next
    INDEX
    Explanations

    references to government programs and funding related to rural issues

    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
     sometimes
    -0.07
    LocalizedString
    -0.07
    pron
    -0.06
    icher
    -0.06
     generally
    -0.06
    _ALIGNMENT
    -0.06
    oÅĻ
    -0.06
    sometimes
    -0.06
    Ľå»º
    -0.06
    .lesson
    -0.06
    POSITIVE LOGITS
     instead
    0.08
    omaly
    0.07
    obia
    0.07
     forth
    0.07
    arend
    0.06
     gấp
    0.06
    asio
    0.06
     alespoÅĪ
    0.06
     ÙģÙĪر
    0.06
    instead
    0.06
    Activations Density 0.046%

    No Known Activations