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. 76528
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in code or programming 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
    appa
    -0.07
    Triangles
    -0.07
    emouth
    -0.07
    radient
    -0.07
    Äįet
    -0.07
    afone
    -0.06
    _Native
    -0.06
    ÑĮого
    -0.06
    ucha
    -0.06
    éģ£
    -0.06
    POSITIVE LOGITS
    Ħ
    0.07
    ĩ
    0.06
    apo
    0.06
    kla
    0.06
    tor
    0.06
     Dane
    0.06
    =Math
    0.06
    -fields
    0.06
    į¼
    0.05
    lo
    0.05
    Activations Density 0.057%

    No Known Activations