© 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. 9-LLAMASCOPE-RES-131K
    11. 94412
    Prev
    Next
    INDEX
    Explanations

    instances of copyright symbols

    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
     mamm
    -0.06
    obot
    -0.06
    cape
    -0.06
     belly
    -0.06
    onic
    -0.06
    09
    -0.05
    izon
    -0.05
    izia
    -0.05
    ensburg
    -0.05
    enburg
    -0.05
    POSITIVE LOGITS
    esModule
    0.08
    elve
    0.07
    .opensource
    0.07
    asty
    0.07
    attles
    0.07
    ãĥ¯ãĥ¼
    0.07
    ırak
    0.07
    iá»ĥu
    0.07
    _DAC
    0.07
    ombat
    0.07
    Activations Density 0.002%

    No Known Activations