© 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. 75621
    Prev
    Next
    INDEX
    Explanations

    themes related to gang involvement and the dynamics of social support and escape

    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
    icc
    -0.07
    째
    -0.07
    ucus
    -0.06
    æĤł
    -0.06
    zte
    -0.06
    igne
    -0.06
     Pes
    -0.06
     Spread
    -0.06
    uche
    -0.06
    enthal
    -0.06
    POSITIVE LOGITS
    (IServiceCollection
    0.07
     adrenaline
    0.07
    ktop
    0.07
    æ°ı
    0.07
     vic
    0.06
    bens
    0.06
     adrenal
    0.06
    _NONNULL
    0.06
    åĢį
    0.06
     Ideal
    0.06
    Activations Density 0.029%

    No Known Activations