© 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. 76863
    Prev
    Next
    INDEX
    Explanations

    code structure, particularly curly braces and parentheses in programming languages

    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
    obus
    -0.06
    èº
    -0.06
    жÑĥ
    -0.06
    .digital
    -0.06
    å¤ķ
    -0.06
    GRA
    -0.05
    olie
    -0.05
    UNG
    -0.05
     Bis
    -0.05
    PRINTF
    -0.05
    POSITIVE LOGITS
    erdale
    0.07
    icles
    0.07
    hack
    0.07
    -toggle
    0.07
    ilha
    0.07
     Kag
    0.07
    _Utils
    0.07
    ermen
    0.06
    éĺ´
    0.06
    hetto
    0.06
    Activations Density 0.032%

    No Known Activations