© 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. 125440
    Prev
    Next
    INDEX
    Explanations

    references to commenting or debating in forums

    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
     Caller
    -0.07
    Caller
    -0.07
    ế
    -0.07
     Kostenlose
    -0.07
    apiro
    -0.07
     callers
    -0.07
     Blanch
    -0.06
    oney
    -0.06
     caller
    -0.06
    elib
    -0.06
    POSITIVE LOGITS
     reply
    0.10
     comment
    0.09
    Reply
    0.08
     replies
    0.08
     replied
    0.08
     response
    0.07
     post
    0.07
     contribution
    0.07
    reply
    0.07
     comments
    0.07
    Activations Density 0.025%

    No Known Activations