© 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. 95517
    Prev
    Next
    INDEX
    Explanations

    Terms related to geographical or statistical categories

    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
    utenberg
    -0.07
    INY
    -0.07
    ilingual
    -0.07
    ÑĢÑĥн
    -0.06
     PMID
    -0.06
    ãĤ½ãĥ³
    -0.06
    efined
    -0.06
     å¨
    -0.06
    менÑĪ
    -0.06
    ftime
    -0.06
    POSITIVE LOGITS
     &
    0.07
    osu
    0.07
    erece
    0.07
    andan
    0.07
     |
    0.06
    echa
    0.06
     and
    0.06
    alim
    0.06
     sortable
    0.06
    rane
    0.06
    Activations Density 0.011%

    No Known Activations