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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77213
    Prev
    Next
    INDEX
    Explanations

    HTTP content types related to application data formats

    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
    .scalablytyped
    -0.09
    .appspot
    -0.07
    olum
    -0.06
    udeau
    -0.06
     Nice
    -0.06
    aghan
    -0.06
    ÙIJر
    -0.06
    empo
    -0.06
    ILLE
    -0.06
     spyOn
    -0.05
    POSITIVE LOGITS
    EDI
    0.08
    /octet
    0.07
    енÑģ
    0.07
    /by
    0.07
    ajor
    0.06
    ·
    0.06
     Bart
    0.06
    icari
    0.06
    ánh
    0.06
    iers
    0.06
    Activations Density 0.001%

    No Known Activations