© 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. 3198
    Prev
    Next
    INDEX
    Explanations

    references to external libraries or resources 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
    ermann
    -0.07
    igham
    -0.07
    orex
    -0.06
    許
    -0.06
    leigh
    -0.06
    èŀº
    -0.06
    _ATOMIC
    -0.06
    _syntax
    -0.06
    asar
    -0.06
    QE
    -0.06
    POSITIVE LOGITS
    fone
    0.06
     Ill
    0.06
     Duy
    0.06
    tero
    0.06
    illon
    0.06
     Ale
    0.06
    rane
    0.06
    itution
    0.06
    kop
    0.06
     tube
    0.06
    Activations Density 0.000%

    No Known Activations