© 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. 17-LLAMASCOPE-RES-131K
    11. 15806
    Prev
    Next
    INDEX
    Explanations

    descriptions related to skin and hair characteristics

    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
    anship
    -0.07
    jure
    -0.07
    agma
    -0.07
    vinc
    -0.07
    voke
    -0.07
    icens
    -0.06
    beb
    -0.06
    antz
    -0.06
    [^
    -0.06
    ibaba
    -0.06
    POSITIVE LOGITS
     naturally
    0.07
     genetically
    0.07
     recess
    0.07
     Ùħز
    0.06
     tendencies
    0.06
     наÑĤÑĥ
    0.06
     natur
    0.06
    кÑĤа
    0.06
     NAT
    0.06
    หย
    0.06
    Activations Density 0.005%

    No Known Activations