© 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 EvalsExportsAPI 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. 118801
    Prev
    Next
    INDEX
    Explanations

    locations and geographical references

    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
     Institute
    -0.07
    ukkit
    -0.07
    ë²
    -0.06
    fromJson
    -0.06
    CJK
    -0.06
    imdi
    -0.06
    ãĥ¼ãĥĵ
    -0.06
    à¥ĩय
    -0.06
    AGMA
    -0.06
    rometer
    -0.06
    POSITIVE LOGITS
    eteor
    0.06
    osti
    0.06
    ucer
    0.06
    ÑĦи
    0.06
    reducers
    0.06
    aves
    0.06
    osaur
    0.06
    stru
    0.06
    ivÄĽ
    0.06
     unders
    0.06
    Activations Density 0.099%

    No Known Activations