© 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. 126371
    Prev
    Next
    INDEX
    Explanations

    variable declarations in programming code

    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
    ulum
    -0.06
    Ñģлов
    -0.06
    mtree
    -0.06
    Architecture
    -0.06
     nic
    -0.06
    izzes
    -0.06
    ist
    -0.06
    iz
    -0.06
    mounted
    -0.06
    обÑĢаж
    -0.06
    POSITIVE LOGITS
    tery
    0.06
     ENUM
    0.06
    iffin
    0.06
    redit
    0.06
    idine
    0.06
    ;amp
    0.06
    utin
    0.06
    ặn
    0.06
    amus
    0.06
    .cmd
    0.06
    Activations Density 0.002%

    No Known Activations