© 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. 119479
    Prev
    Next
    INDEX
    Explanations

    words related to social behavior issues and public disturbances

    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
    üçük
    -0.07
    ikat
    -0.07
     addCriterion
    -0.07
    .digital
    -0.07
    ieder
    -0.07
    inke
    -0.07
    upported
    -0.07
    ÏĬ
    -0.07
    phy
    -0.07
    çĿ£
    -0.07
    POSITIVE LOGITS
     behavior
    0.10
     conduct
    0.10
     Behavior
    0.08
     behaviour
    0.08
     disorder
    0.08
    behavior
    0.08
     Disorder
    0.08
    è¡Į为
    0.07
     Conduct
    0.07
    liness
    0.07
    Activations Density 0.006%

    No Known Activations