© 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. 125964
    Prev
    Next
    INDEX
    Explanations

    phrases related to professions and professional backgrounds

    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
    142
    -0.07
    urement
    -0.06
    ands
    -0.06
    annon
    -0.06
    152
    -0.06
    arts
    -0.06
    quirrel
    -0.06
    ertz
    -0.06
    abyrin
    -0.06
    irma
    -0.06
    POSITIVE LOGITS
    _NOTICE
    0.07
     rendre
    0.06
    _Write
    0.06
     write
    0.06
    gere
    0.06
    render
    0.06
    icz
    0.06
    uraa
    0.06
    æĽ²
    0.06
    odyn
    0.06
    Activations Density 0.014%

    No Known Activations