Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5222
    Prev
    Next
    INDEX
    Explanations

    references to technical or scientific processes and terminology

    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
    ISCO
    -0.10
    cctor
    -0.09
    ICC
    -0.08
    'gc
    -0.08
    νÏĮ
    -0.08
    EIF
    -0.08
    ÑĢаÑģÑĤа
    -0.08
    _________________↵↵
    -0.08
     nackte
    -0.08
    .shows
    -0.08
    POSITIVE LOGITS
    le
    0.07
       
    0.07
    éĢģæĸĻçĦ¡æĸĻ
    0.06
    z
    0.06
    aut
    0.06
    out
    0.06
    ved
    0.06
    ente
    0.06
    ire
    0.06
    im
    0.06
    Activations Density 0.455%

    No Known Activations