© 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. 29458
    Prev
    Next
    INDEX
    Explanations

    references to string or object types in programming languages

    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
    afort
    -0.07
    aul
    -0.07
    áo
    -0.07
    atal
    -0.07
    zzo
    -0.07
    raud
    -0.07
    resco
    -0.06
    unsch
    -0.06
    endir
    -0.06
    ekler
    -0.06
    POSITIVE LOGITS
    .mapbox
    0.06
    едини
    0.06
    'field
    0.06
    ëĭī
    0.06
    kah
    0.06
    _NR
    0.06
    ?url
    0.06
    -preview
    0.06
    oj
    0.06
    nic
    0.06
    Activations Density 0.001%

    No Known Activations