© 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. 17-LLAMASCOPE-RES-131K
    11. 55975
    Prev
    Next
    INDEX
    Explanations

    programming-related functions and methods used in coding

    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
    215
    -0.07
    kou
    -0.07
    nox
    -0.07
    ckt
    -0.06
    avers
    -0.06
    jab
    -0.06
    олж
    -0.06
    illas
    -0.06
    ovic
    -0.06
    iban
    -0.06
    POSITIVE LOGITS
    stantiate
    0.08
    ä¸Ģä¸ĭ
    0.07
    ÏĦαι
    0.06
    gaard
    0.06
     hala
    0.06
    าà¸ĩ
    0.06
    uppe
    0.06
     promin
    0.06
    -ÑĤаки
    0.06
    PLE
    0.06
    Activations Density 0.038%

    No Known Activations