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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5167
    Prev
    Next
    INDEX
    Explanations

    terms related to fictional narratives or fabrications

    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
    oref
    -0.07
    ÑĥÑĩа
    -0.07
    amework
    -0.07
    /el
    -0.07
    asion
    -0.07
    orgia
    -0.07
    _regularizer
    -0.06
    .LENGTH
    -0.06
    estro
    -0.06
     Ki
    -0.06
    POSITIVE LOGITS
    ideal
    0.09
     ideal
    0.08
    ized
    0.07
     scenarios
    0.07
    ti
    0.07
    location
    0.07
    itics
    0.07
     scenario
    0.07
     Ideal
    0.06
     teng
    0.06
    Activations Density 0.022%

    No Known Activations