© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55540
    Prev
    Next
    INDEX
    Explanations

    questions related to perceptions and expectations

    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
    udas
    -0.07
     basically
    -0.07
    eza
    -0.07
     ÑĩиÑģлÑĸ
    -0.07
    ả
    -0.07
    gne
    -0.07
    à¸Ńà¸Ķ
    -0.07
    .sys
    -0.07
    gzip
    -0.07
    rain
    -0.07
    POSITIVE LOGITS
     nor
    0.19
     anymore
    0.18
     necessarily
    0.13
    nor
    0.13
     Nor
    0.11
    Nor
    0.10
     either
    0.10
     EITHER
    0.09
     ani
    0.09
     NOR
    0.09
    Activations Density 0.020%

    No Known Activations