© 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. 1175
    Prev
    Next
    INDEX
    Explanations

    key terms related to choices and personal decisions

    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
    .esp
    -0.07
    inel
    -0.06
     Trot
    -0.06
     as
    -0.06
     Gross
    -0.06
    Stars
    -0.06
     rather
    -0.06
     Stars
    -0.06
    alar
    -0.06
    sv
    -0.06
    POSITIVE LOGITS
     ÙģØ¥ÙĨ
    0.10
     thì
    0.08
    IIIK
    0.07
    æ´ģ
    0.07
     ÙģÙĤد
    0.07
     mastur
    0.07
    turnstile
    0.07
    >Main
    0.07
    ENE
    0.07
    #
    0.07
    Activations Density 0.010%

    No Known Activations