© 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. 61690
    Prev
    Next
    INDEX
    Explanations

    parentheses and related markers of additional information or clarifications

    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
    ience
    -0.07
    /REC
    -0.07
     olab
    -0.07
     Vác
    -0.07
    STYPE
    -0.06
     Shepard
    -0.06
    atr
    -0.06
    âu
    -0.06
     ÄijÃłi
    -0.06
    (æĹ¥
    -0.06
    POSITIVE LOGITS
    cape
    0.07
    tica
    0.07
    nage
    0.06
     whom
    0.06
    oris
    0.06
     alias
    0.06
    boro
    0.06
    alias
    0.06
     born
    0.06
    48
    0.06
    Activations Density 0.017%

    No Known Activations