© 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. 57645
    Prev
    Next
    INDEX
    Explanations

    technical references and parameters related to configuration files

    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
    iani
    -0.07
    ogui
    -0.07
    ori
    -0.07
    ionage
    -0.06
    rior
    -0.06
    /mit
    -0.06
    uckle
    -0.06
    spd
    -0.06
    abil
    -0.06
    ubat
    -0.06
    POSITIVE LOGITS
    ruh
    0.07
    ##_
    0.07
    kaar
    0.06
     sund
    0.06
    VG
    0.06
    eum
    0.06
     mastur
    0.06
    #/
    0.06
    ãģĭãĤĬ
    0.06
    ìŀ¡
    0.06
    Activations Density 0.016%

    No Known Activations