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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83277
    Prev
    Next
    INDEX
    Explanations

    advice related to skin care and health

    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
    ãĥ³ãĥĩ
    -0.07
    strand
    -0.06
    ãĥĨãĥ«
    -0.06
    asso
    -0.06
    ObjectType
    -0.06
    rotch
    -0.06
    ÅĻÃŃd
    -0.06
    undy
    -0.06
    ÙĪØ´
    -0.06
    ÑŁ
    -0.06
    POSITIVE LOGITS
     Enh
    0.10
     Enhancement
    0.10
     enh
    0.10
     enhance
    0.10
     enhancement
    0.09
     enhances
    0.09
    Enh
    0.09
     enhancements
    0.09
     prolong
    0.09
    enh
    0.09
    Activations Density 0.092%

    No Known Activations