© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84041
    Prev
    Next
    INDEX
    Explanations

    mentions of sodium and related chemical terms

    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
    azzi
    -0.07
    lio
    -0.07
    thinkable
    -0.07
     Fleming
    -0.06
     Colony
    -0.06
    tera
    -0.06
    oti
    -0.06
    .registration
    -0.06
    chos
    -0.06
    imax
    -0.06
    POSITIVE LOGITS
    á»ħ
    0.07
    Äįet
    0.06
    s
    0.06
    çĽ
    0.06
     Went
    0.06
    richt
    0.06
    inds
    0.06
    orus
    0.06
     Taste
    0.06
     bic
    0.06
    Activations Density 0.003%

    No Known Activations