© 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. 129092
    Prev
    Next
    INDEX
    Explanations

    terms related to data fetching operations or commands

    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
    led
    -0.07
    ymous
    -0.07
    Ø©
    -0.07
    ç±į
    -0.06
    ajas
    -0.06
    ned
    -0.06
    екÑģи
    -0.06
    atisch
    -0.06
    ìłģìľ¼ë¡ľ
    -0.06
     Affero
    -0.06
    POSITIVE LOGITS
    (es
    0.12
    es
    0.11
    ä¸įåĪ°
    0.10
    s
    0.10
    ments
    0.09
    ers
    0.09
    ables
    0.08
    ability
    0.08
    esse
    0.08
    ES
    0.08
    Activations Density 0.008%

    No Known Activations