© 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. 106782
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy recommendations and council discussions

    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
    ISCO
    -0.07
    ovi
    -0.07
    reach
    -0.06
    èľľ
    -0.06
    Britain
    -0.06
     Conte
    -0.06
    ORIZ
    -0.06
    readcr
    -0.06
    -ng
    -0.06
    phin
    -0.06
    POSITIVE LOGITS
     Whip
    0.06
    -placeholder
    0.06
    ugar
    0.06
    ickle
    0.06
    adol
    0.06
    Had
    0.06
     Suff
    0.06
     Sud
    0.06
    andle
    0.06
     conven
    0.06
    Activations Density 0.002%

    No Known Activations