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. 56062
    Prev
    Next
    INDEX
    Explanations

    structures and elements related to programming or code syntax

    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
    è´Ł
    -0.07
    vou
    -0.07
    agar
    -0.07
    avad
    -0.06
    azen
    -0.06
    .Escape
    -0.06
    unami
    -0.06
    ahoma
    -0.06
    cio
    -0.06
    abet
    -0.06
    POSITIVE LOGITS
     Wol
    0.07
     BSD
    0.07
    IDES
    0.07
     acceler
    0.06
    æıIJ示
    0.06
    .bunifuFlatButton
    0.06
    (iOS
    0.06
     acceleration
    0.06
    _TRACE
    0.06
    BSD
    0.06
    Activations Density 0.032%

    No Known Activations