© 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. 77346
    Prev
    Next
    INDEX
    Explanations

    references to locations or places

    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
    unas
    -0.08
    reuse
    -0.08
    apphire
    -0.07
    ists
    -0.07
    phies
    -0.07
    wayne
    -0.07
    lica
    -0.07
    ucid
    -0.07
    zeit
    -0.07
    áce
    -0.07
    POSITIVE LOGITS
    /people
    0.08
     where
    0.08
    ê³³
    0.07
     Jacobs
    0.07
    кÑĢаÑĹ
    0.07
    liness
    0.06
    emento
    0.06
    umbing
    0.06
    dÄĽ
    0.06
    ãģ§ãģ®
    0.06
    Activations Density 0.021%

    No Known Activations