© 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. 894
    Prev
    Next
    INDEX
    Explanations

    references to acting and performance in film

    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
    rary
    -0.08
    affer
    -0.08
    oser
    -0.08
    648
    -0.07
    avou
    -0.07
    797
    -0.06
    676
    -0.06
    642
    -0.06
    rawer
    -0.06
     Ahead
    -0.06
    POSITIVE LOGITS
    enstein
    0.06
     publicly
    0.06
    ATEGORY
    0.06
     onCreateViewHolder
    0.06
    ANDLE
    0.06
     when
    0.06
    maz
    0.05
    duck
    0.05
    xml
    0.05
    gr
    0.05
    Activations Density 0.030%

    No Known Activations