© 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. 126421
    Prev
    Next
    INDEX
    Explanations

    references to social issues and acts of kindness in difficult situations

    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
     ep
    -0.07
    ozor
    -0.06
     pard
    -0.06
    haus
    -0.06
     Guild
    -0.06
    ored
    -0.06
    ores
    -0.06
    erte
    -0.06
    ải
    -0.05
    ÑĥÑĢн
    -0.05
    POSITIVE LOGITS
     Terrorism
    0.07
     unity
    0.07
    olerance
    0.07
    Äįan
    0.07
    affected
    0.07
    assin
    0.07
     terrorism
    0.06
    symbols
    0.06
    parm
    0.06
    Affected
    0.06
    Activations Density 0.033%

    No Known Activations