© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76277
    Prev
    Next
    INDEX
    Explanations

    references to the organization and its activities

    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
    anke
    -0.08
    ÑĢÑĸб
    -0.07
    ITY
    -0.07
    est
    -0.07
    hof
    -0.07
    raith
    -0.07
    lok
    -0.07
     interp
    -0.07
    ÅĦst
    -0.07
     Aires
    -0.07
    POSITIVE LOGITS
    uator
    0.12
    uar
    0.11
    uated
    0.10
    inic
    0.09
    uate
    0.09
    uating
    0.08
    UAL
    0.08
    uation
    0.08
    uary
    0.08
    ual
    0.07
    Activations Density 0.026%

    No Known Activations