© 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. 16632
    Prev
    Next
    INDEX
    Explanations

    structured discussions about age-related content and societal expectations

    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
    ÐĿÐĨ
    -0.08
    -caption
    -0.07
    /respond
    -0.07
     Brewery
    -0.07
    affer
    -0.07
    /contact
    -0.07
    avou
    -0.07
    ¶Į
    -0.07
    entai
    -0.07
    .guid
    -0.07
    POSITIVE LOGITS
     slightly
    0.07
     speaker
    0.07
     speakers
    0.06
     emphasis
    0.06
    -spe
    0.06
     Speaker
    0.06
    preter
    0.06
    hardt
    0.06
    lyn
    0.06
    speaker
    0.06
    Activations Density 0.003%

    No Known Activations