© 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. 71357
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and elements within 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
    ços
    -0.06
    OperationException
    -0.06
     Dodd
    -0.06
     ç¯
    -0.06
    ighton
    -0.06
     ens
    -0.05
    imson
    -0.05
    .makeText
    -0.05
    abbo
    -0.05
    лÑıÑħ
    -0.05
    POSITIVE LOGITS
    _vue
    0.08
     Leaf
    0.07
    __*/
    0.07
    ầu
    0.06
    abe
    0.06
    rowable
    0.06
    .hex
    0.06
    UILTIN
    0.06
    (Constructor
    0.06
    MAND
    0.06
    Activations Density 0.015%

    No Known Activations