© 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. 15-LLAMASCOPE-RES-131K
    11. 90099
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize personal needs and collective experiences

    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
    nie
    -0.07
    isma
    -0.07
    ież
    -0.06
    path
    -0.06
    ibri
    -0.06
    266
    -0.06
     ie
    -0.06
     often
    -0.06
     ones
    -0.06
    ima
    -0.06
    POSITIVE LOGITS
     happening
    0.08
    uco
    0.07
     Wrong
    0.07
    rych
    0.07
    åħ³äºİ
    0.07
     má»įi
    0.06
    done
    0.06
     happened
    0.06
    lluminate
    0.06
    à¸Īำ
    0.06
    Activations Density 0.020%

    No Known Activations