© 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 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. 17-LLAMASCOPE-RES-131K
    11. 57396
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and punctuation marks

    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
     à¤
    -0.08
     Burl
    -0.07
    ãĤ¿ãĥ«
    -0.07
    ÙĤÙĦ
    -0.07
     Rut
    -0.07
     Porno
    -0.07
    alley
    -0.07
     é¹
    -0.07
    #
    -0.06
     ÑģÑĤоÑĢонÑĭ
    -0.06
    POSITIVE LOGITS
    heit
    0.07
     dec
    0.06
     Fortune
    0.06
    neh
    0.06
     SelectList
    0.06
    aden
    0.05
    igit
    0.05
    /internal
    0.05
     internal
    0.05
     bi
    0.05
    Activations Density 0.000%

    No Known Activations