© 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. 15-LLAMASCOPE-RES-131K
    11. 104001
    Prev
    Next
    INDEX
    Explanations

    phrases expressing denial or resistance to acceptance or tolerance

    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
    onth
    -0.06
     OT
    -0.06
    yy
    -0.06
    ual
    -0.06
     ventil
    -0.06
     somewhat
    -0.06
     slightly
    -0.06
     rather
    -0.06
     fri
    -0.05
    amil
    -0.05
    POSITIVE LOGITS
     anymore
    0.11
    iveau
    0.08
    geist
    0.07
    izin
    0.07
    -thumb
    0.07
    ãĤĿ
    0.07
    erce
    0.07
    ennes
    0.07
    (DBG
    0.07
    .histogram
    0.07
    Activations Density 0.020%

    No Known Activations