© 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. 61713
    Prev
    Next
    INDEX
    Explanations

    references to imagination and visual imagery

    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
    @student
    -0.07
    odom
    -0.07
    obraz
    -0.07
    apr
    -0.07
    assi
    -0.07
    áp
    -0.06
    azel
    -0.06
    _PIX
    -0.06
    dete
    -0.06
    urv
    -0.06
    POSITIVE LOGITS
     závÄĽ
    0.06
    RLF
    0.06
     bil
    0.06
    memset
    0.06
     DS
    0.06
    //------------------------------------------------------------------------------↵↵
    0.06
    laughs
    0.06
    ledi
    0.06
    곤
    0.06
     FontStyle
    0.06
    Activations Density 0.003%

    No Known Activations