© 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. 15-LLAMASCOPE-RES-131K
    6. 90133
    Prev
    Next
    INDEX
    Explanations

    programming constructs and components related to definitions, object representations, and function calls

    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
     Bers
    -0.08
    -BEGIN
    -0.07
    assin
    -0.07
    (TM
    -0.07
     CrossRef
    -0.07
    Äįet
    -0.06
    ocks
    -0.06
    olatile
    -0.06
     Petty
    -0.06
    =*/
    -0.06
    POSITIVE LOGITS
     sut
    0.07
    upp
    0.07
    /Instruction
    0.06
    alam
    0.06
    еÑĢина
    0.06
    eler
    0.06
    ourcem
    0.06
     latter
    0.06
    uz
    0.06
    éļĨ
    0.06
    Activations Density 0.023%

    No Known Activations