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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103266
    Prev
    Next
    INDEX
    Explanations

    code structures, particularly function definitions and their return statements

    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
    s
    -0.08
    unta
    -0.06
    ichtig
    -0.06
    Ùĩ
    -0.06
    .ly
    -0.06
     stay
    -0.06
    morgan
    -0.06
    iones
    -0.05
    ot
    -0.05
    otte
    -0.05
    POSITIVE LOGITS
     Shr
    0.07
    shr
    0.07
    Cro
    0.07
    ãĤ¯ãĥŃ
    0.07
     wur
    0.07
    Ñİк
    0.07
    ãĥ³ãĥĩãĤ£
    0.07
     vÃŃde
    0.07
     Carp
    0.07
    ĥ½
    0.06
    Activations Density 0.001%

    No Known Activations