© 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. 17-LLAMASCOPE-RES-131K
    6. 76144
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with quantities and statistics

    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
     benzer
    -0.06
    %C
    -0.06
     relevant
    -0.05
    less
    -0.05
     reb
    -0.05
     dopad
    -0.05
    зÑĮ
    -0.05
    ÑģÑĤи
    -0.05
    зи
    -0.05
     Gram
    -0.05
    POSITIVE LOGITS
    ména
    0.08
    ฯ
    0.08
    usan
    0.07
    apol
    0.07
    athom
    0.07
    :animated
    0.07
    akedown
    0.07
    elik
    0.07
    altura
    0.07
    ).__
    0.07
    Activations Density 0.021%

    No Known Activations