© 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. 87363
    Prev
    Next
    INDEX
    Explanations

    references to illegal activities or conditions

    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
    yll
    -0.06
    inel
    -0.06
     relatively
    -0.06
    utral
    -0.06
    comings
    -0.06
    slaught
    -0.06
    ãģıãĤĭ
    -0.06
    VML
    -0.06
    .microsoft
    -0.06
    BYTES
    -0.06
    POSITIVE LOGITS
    ities
    0.10
    /il
    0.10
    /un
    0.08
    ional
    0.07
    ely
    0.07
    275
    0.07
    /question
    0.07
    itics
    0.07
    amat
    0.07
    amate
    0.06
    Activations Density 0.007%

    No Known Activations