© 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. 16568
    Prev
    Next
    INDEX
    Explanations

    references to coercive actions or allegations of misconduct

    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
    antity
    -0.08
    affen
    -0.08
    ardin
    -0.07
     {\↵
    -0.07
    ôn
    -0.07
    rocess
    -0.07
     simplex
    -0.07
    urry
    -0.07
    ngth
    -0.07
    ennent
    -0.07
    POSITIVE LOGITS
    appropri
    0.06
     Genius
    0.06
    inski
    0.06
     unwanted
    0.06
     creep
    0.06
     inappropriate
    0.06
    mented
    0.06
     ilma
    0.06
    aged
    0.06
    way
    0.05
    Activations Density 0.004%

    No Known Activations