© 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. 117585
    Prev
    Next
    INDEX
    Explanations

    instances of the word "some" and its variations, indicating a theme of generalization or categorization

    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
    undy
    -0.07
    947
    -0.07
    enz
    -0.06
     aur
    -0.06
    anel
    -0.06
    oyer
    -0.06
    124
    -0.06
    sec
    -0.06
    nz
    -0.06
    inine
    -0.06
    POSITIVE LOGITS
    ErrorException
    0.09
    оÑģÑĤи
    0.07
     Assembly
    0.07
    .Percent
    0.07
     say
    0.07
    assembly
    0.07
    cents
    0.06
    lee
    0.06
    icina
    0.06
    how
    0.06
    Activations Density 0.023%

    No Known Activations