© 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. 71362
    Prev
    Next
    INDEX
    Explanations

    instances of criticism towards various subjects

    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
    .scenes
    -0.07
    uzu
    -0.07
    kits
    -0.07
     плаÑģÑĤи
    -0.07
    rox
    -0.07
    ÏĢει
    -0.07
    eya
    -0.07
    PÅĻÃŃ
    -0.07
    ey
    -0.07
    неÑģ
    -0.07
    POSITIVE LOGITS
    -minded
    0.07
    Crit
    0.07
    hythm
    0.07
    ingers
    0.06
    asters
    0.06
     Crit
    0.06
    557
    0.06
    unction
    0.06
     Morgan
    0.06
    ably
    0.06
    Activations Density 0.013%

    No Known Activations