© 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. 15940
    Prev
    Next
    INDEX
    Explanations

    elements related to fictional narratives and their settings

    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
    лив
    -0.07
     ÑģбоÑĢ
    -0.06
    706
    -0.06
     CLEAN
    -0.06
     validationResult
    -0.06
    @student
    -0.06
     Incontri
    -0.06
    енз
    -0.06
     cave
    -0.06
    _PATCH
    -0.06
    POSITIVE LOGITS
     dyst
    0.08
     ut
    0.07
     Resistance
    0.07
    /post
    0.07
     regime
    0.06
     reproductive
    0.06
    Resistance
    0.06
    reme
    0.06
     nucle
    0.06
    Aliases
    0.06
    Activations Density 0.001%

    No Known Activations