Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96032
    Prev
    Next
    INDEX
    Explanations

    terms related to rejection or disapproval

    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
    uckle
    -0.08
    -thirds
    -0.07
    sey
    -0.06
    ux
    -0.06
    utton
    -0.06
    ellen
    -0.06
    /read
    -0.06
    UX
    -0.06
    /email
    -0.06
    vor
    -0.06
    POSITIVE LOGITS
    ably
    0.09
    ively
    0.09
    /ref
    0.08
    resher
    0.08
    imated
    0.07
     hur
    0.07
    æİī
    0.07
    genes
    0.07
     SvÄĽt
    0.07
    rance
    0.07
    Activations Density 0.010%

    No Known Activations