© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90336
    Prev
    Next
    INDEX
    Explanations

    classes and functions related to constructors in programming

    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
    oci
    -0.07
    ocre
    -0.06
    itches
    -0.06
    iedy
    -0.06
    lein
    -0.06
     lamin
    -0.06
    ixe
    -0.06
    inki
    -0.06
    atr
    -0.06
    able
    -0.06
    POSITIVE LOGITS
     Wonderland
    0.07
     Fé
    0.07
    éºĹ
    0.06
    Uvs
    0.06
    _ASSUME
    0.06
     Sá»Ń
    0.06
    ewood
    0.06
    _Runtime
    0.06
    _budget
    0.06
    uhl
    0.06
    Activations Density 0.000%

    No Known Activations