© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126438
    Prev
    Next
    INDEX
    Explanations

    instances of arrays in code

    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
    TemplateName
    -0.07
    ArrayOf
    -0.06
    011
    -0.06
    _HOR
    -0.06
    ling
    -0.06
    entities
    -0.06
    ÑĥÑī
    -0.06
    iom
    -0.06
    .dk
    -0.06
    iba
    -0.06
    POSITIVE LOGITS
    ÃľR
    0.07
    å¿Ĺ
    0.06
    ernel
    0.06
    VERRIDE
    0.06
    rian
    0.06
    latlong
    0.06
    zilla
    0.06
    RG
    0.06
    chied
    0.06
    ERRU
    0.06
    Activations Density 0.002%

    No Known Activations