© 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. 30969
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" and its variations to highlight increases or additional information

    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
    abay
    -0.07
    iry
    -0.07
    .experimental
    -0.07
    åļ
    -0.07
    624
    -0.07
    acades
    -0.07
    ucht
    -0.06
    atter
    -0.06
    successfully
    -0.06
     obec
    -0.06
    POSITIVE LOGITS
    au
    0.07
     coverage
    0.06
     bite
    0.06
    oplay
    0.06
     Coverage
    0.06
    coverage
    0.06
    ÑĩаÑĤ
    0.06
     ++)
    0.06
    udit
    0.06
    ereco
    0.06
    Activations Density 0.018%

    No Known Activations