© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82752
    Prev
    Next
    INDEX
    Explanations

    code-related terms and formatting commands

    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
    ertz
    -0.07
    izi
    -0.06
    ateur
    -0.06
    DM
    -0.06
    amo
    -0.06
    rchive
    -0.06
    amburg
    -0.05
    -wow
    -0.05
    ymoon
    -0.05
    artin
    -0.05
    POSITIVE LOGITS
    uur
    0.08
    _cpp
    0.07
     ÃĿ
    0.07
    .dtd
    0.07
     Fowler
    0.07
    ÏĮÏĦη
    0.07
    _EOL
    0.07
    áy
    0.06
    lage
    0.06
    .getInteger
    0.06
    Activations Density 0.000%

    No Known Activations