© 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. 2902
    Prev
    Next
    INDEX
    Explanations

    components of character relationships and instances of transformation

    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
    ohana
    -0.09
    _Lean
    -0.09
    TEGER
    -0.08
    UrlParser
    -0.08
    illez
    -0.08
    _Tis
    -0.08
    .scalablytyped
    -0.08
    amy
    -0.08
    ñas
    -0.08
    SupportedContent
    -0.08
    POSITIVE LOGITS
     BOT
    0.06
    noch
    0.06
     stereotype
    0.06
     chic
    0.06
     man
    0.05
     carriers
    0.05
     Sad
    0.05
     lapse
    0.05
    ling
    0.05
     boy
    0.05
    Activations Density 0.107%

    No Known Activations