© 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. 125813
    Prev
    Next
    INDEX
    Explanations

    references to audience dynamics and interactions

    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
     karak
    -0.07
     heading
    -0.07
    ÄįÃŃ
    -0.07
    تس
    -0.06
    .bt
    -0.06
    ippi
    -0.06
    æ¯
    -0.06
     headed
    -0.06
    éf
    -0.06
    ads
    -0.06
    POSITIVE LOGITS
     audience
    0.08
     Audience
    0.07
    -feedback
    0.07
    ples
    0.07
    wf
    0.07
    AUD
    0.07
     demographic
    0.06
    fv
    0.06
    feedback
    0.06
     demographics
    0.06
    Activations Density 0.040%

    No Known Activations