© 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. 9-LLAMASCOPE-RES-131K
    11. 95625
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "see" and its variations in different contexts

    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
    cs
    -0.08
    sten
    -0.08
    stp
    -0.07
    ader
    -0.07
    cul
    -0.07
    ized
    -0.06
    icens
    -0.06
    姿
    -0.06
    cts
    -0.06
    erie
    -0.06
    POSITIVE LOGITS
    /he
    0.09
     cref
    0.07
    dust
    0.07
    /list
    0.07
     xét
    0.07
     Dün
    0.07
    erville
    0.07
    eof
    0.07
    รวม
    0.06
    -fw
    0.06
    Activations Density 0.090%

    No Known Activations