© 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. 40022
    Prev
    Next
    INDEX
    Explanations

    phrases relating to perceptions and impressions of appearance or existence

    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
    iddi
    -0.08
    zew
    -0.07
    edly
    -0.07
    indy
    -0.06
    «
    -0.06
    _:*
    -0.06
    orf
    -0.06
    ily
    -0.06
     Ty
    -0.06
    ootball
    -0.06
    POSITIVE LOGITS
    /how
    0.09
    herits
    0.08
    ueblo
    0.07
    ÑĪкÑĥ
    0.07
    ãĢģä½ķ
    0.06
     Cooke
    0.06
     exactly
    0.06
    /is
    0.06
    isÃŃ
    0.06
    283
    0.06
    Activations Density 0.033%

    No Known Activations