© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3975
    Prev
    Next
    INDEX
    Explanations

    content related to responsibility and consequences in various 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
    .override
    -0.08
    wig
    -0.07
    .Override
    -0.07
    ÙĬس
    -0.06
     пÑĢава
    -0.06
    interrupt
    -0.06
    ospace
    -0.06
     kost
    -0.06
     Fate
    -0.06
    oltage
    -0.06
    POSITIVE LOGITS
     presence
    0.09
     change
    0.07
    gone
    0.07
     Presence
    0.07
     lack
    0.07
     proximity
    0.07
    Presence
    0.07
     actions
    0.06
    olicies
    0.06
     decisions
    0.06
    Activations Density 0.078%

    No Known Activations