© 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. 90121
    Prev
    Next
    INDEX
    Explanations

    punctuation and expressions of accountability

    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
    ÃĹ↵↵
    -0.08
    ichert
    -0.07
    drawer
    -0.06
    culate
    -0.06
    обÑĢаÐ
    -0.06
    ãĤĨ
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    ë°ĶìĿ´
    -0.06
    одав
    -0.06
    ouden
    -0.06
    POSITIVE LOGITS
    epar
    0.07
    Į¨
    0.06
    mlin
    0.06
    ãģĵãģ¨ãģ§
    0.06
     pdf
    0.06
     Feinstein
    0.06
    884
    0.06
    ripp
    0.06
    ropp
    0.06
    iene
    0.06
    Activations Density 0.000%

    No Known Activations