© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61693
    Prev
    Next
    INDEX
    Explanations

    expressions of acceptance and freedom in personal and artistic identity

    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
    rava
    -0.07
    /drivers
    -0.07
    endor
    -0.07
    æ¢
    -0.07
    oleÄį
    -0.07
    ove
    -0.07
    iset
    -0.07
    quiz
    -0.06
     prostitutas
    -0.06
    mand
    -0.06
    POSITIVE LOGITS
     occasionally
    0.09
     admitting
    0.07
     occasional
    0.07
     admissions
    0.07
    rik
    0.06
     admitted
    0.06
    ask
    0.06
    $MESS
    0.06
     McCl
    0.06
     Occasionally
    0.06
    Activations Density 0.026%

    No Known Activations