© 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. 126013
    Prev
    Next
    INDEX
    Explanations

    concepts related to agility and adaptability

    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
    anger
    -0.08
    sel
    -0.08
    füg
    -0.08
    ç±į
    -0.08
    sv
    -0.07
    angers
    -0.07
    лива
    -0.07
    sWith
    -0.07
    verbosity
    -0.07
    ses
    -0.07
    POSITIVE LOGITS
    ly
    0.06
    /ag
    0.06
    ized
    0.06
    ness
    0.06
    ged
    0.06
     dramatic
    0.06
    iously
    0.06
    ient
    0.06
    kt
    0.06
     adopt
    0.06
    Activations Density 0.001%

    No Known Activations