© 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. 38975
    Prev
    Next
    INDEX
    Explanations

    words indicating strong recommendations or intentions

    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
    ãģ¡ãĤī
    -0.07
    ollen
    -0.07
    aku
    -0.06
    /constants
    -0.06
    verture
    -0.06
    azu
    -0.06
    ngth
    -0.06
    имÑĥ
    -0.06
    atica
    -0.06
    burgh
    -0.06
    POSITIVE LOGITS
    cel
    0.07
    .Struct
    0.07
    orny
    0.07
     again
    0.06
     rall
    0.06
    umer
    0.06
    ign
    0.06
    ltk
    0.06
    cargo
    0.06
    ceph
    0.05
    Activations Density 0.006%

    No Known Activations