© 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. 124237
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or codes associated with various entities

    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
    çĽijåIJ¬é¡µéĿ¢
    -0.09
    окон
    -0.08
    rol
    -0.08
    errer
    -0.08
    #
    -0.07
    azo
    -0.07
    ATAL
    -0.07
    MOTE
    -0.07
    auc
    -0.07
    lok
    -0.07
    POSITIVE LOGITS
    s
    0.15
    âĢ²
    0.11
    âĢ³
    0.09
    sus
    0.09
    ska
    0.08
    sand
    0.07
    'er
    0.07
    ï¸ı
    0.07
    -Ñħ
    0.07
    -й
    0.06
    Activations Density 0.046%

    No Known Activations