© 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. 129112
    Prev
    Next
    INDEX
    Explanations

    references to movies, particularly focusing on genres like comedies and horrors

    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
    athan
    -0.06
    orate
    -0.06
    .tm
    -0.06
     Wikip
    -0.06
    ikel
    -0.06
    egl
    -0.06
    enga
    -0.06
    lah
    -0.06
    omic
    -0.06
     deadlock
    -0.06
    POSITIVE LOGITS
    åľŃ
    0.06
     Folk
    0.06
    pios
    0.06
    vens
    0.06
    溶
    0.06
    以åIJİ
    0.06
    .unsubscribe
    0.05
    SPATH
    0.05
    ÑĨий
    0.05
    itnÃŃ
    0.05
    Activations Density 0.009%

    No Known Activations