© 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. 29607
    Prev
    Next
    INDEX
    Explanations

    references to software versioning and descriptions

    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
    âm
    -0.08
    avier
    -0.07
    žit
    -0.07
    аÑĢÑı
    -0.07
     Slash
    -0.07
    们
    -0.07
    -strip
    -0.06
    dek
    -0.06
    боÑĤ
    -0.06
     Strip
    -0.06
    POSITIVE LOGITS
    version
    0.07
    (version
    0.07
     Version
    0.07
     version
    0.06
    _UTF
    0.06
    rub
    0.06
    VERSION
    0.06
    _version
    0.06
    itan
    0.06
    Version
    0.06
    Activations Density 0.002%

    No Known Activations