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

    Neuronpedia

    Jacobian LensNEW
    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. 78441
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gone" and its derivatives

    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
    Ïģιά
    -0.07
    acia
    -0.07
    .scalablytyped
    -0.07
    rieg
    -0.07
    omaly
    -0.07
    roz
    -0.07
    ummer
    -0.07
     киÑĢ
    -0.07
    alis
    -0.07
    ars
    -0.06
    POSITIVE LOGITS
    fish
    0.06
    gone
    0.06
    /un
    0.06
     typo
    0.06
    alion
    0.06
     Gone
    0.06
    .habbo
    0.06
    vez
    0.05
    @g
    0.05
    idges
    0.05
    Activations Density 0.003%

    No Known Activations