© 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. 15125
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols commonly used in programming

    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
    uto
    -0.06
     Mint
    -0.06
    ent
    -0.06
    10
    -0.05
     Figure
    -0.05
    -out
    -0.05
    chu
    -0.05
     Bent
    -0.05
    âĢ¦
    -0.05
    atty
    -0.05
    POSITIVE LOGITS
    ROAD
    0.08
    âĻ¡
    0.08
    μβ
    0.08
    ZF
    0.07
     dateString
    0.07
    Apis
    0.07
    Fld
    0.07
    ãĥ³ãĥĸ
    0.07
     VÅ¡ech
    0.07
    undle
    0.07
    Activations Density 0.000%

    No Known Activations