© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105477
    Prev
    Next
    INDEX
    Explanations

    code syntax elements such as braces, function definitions, and variable declarations

    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
    bou
    -0.07
    ipay
    -0.07
    ustos
    -0.07
    _foreign
    -0.07
    aison
    -0.06
    ismet
    -0.06
    argent
    -0.06
    ¯
    -0.06
    abwe
    -0.06
    ullet
    -0.06
    POSITIVE LOGITS
     BST
    0.07
    ÙĦاØŃ
    0.07
    509
    0.06
    aux
    0.06
     commons
    0.06
    __':↵
    0.06
    inta
    0.06
     class
    0.06
    Corp
    0.05
     Commons
    0.05
    Activations Density 0.009%

    No Known Activations