© 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. 119547
    Prev
    Next
    INDEX
    Explanations

    references to the character "Snitch" or related concepts in narratives

    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
    acades
    -0.08
    yms
    -0.07
    IGN
    -0.07
    encent
    -0.07
    .gwt
    -0.07
    ropoda
    -0.07
    amente
    -0.07
    antine
    -0.07
    ombine
    -0.07
    roupon
    -0.07
    POSITIVE LOGITS
     sn
    0.10
    /sn
    0.09
     Sn
    0.08
    sn
    0.08
    .Sn
    0.07
    oring
    0.07
    (sn
    0.07
     dro
    0.07
     Lies
    0.07
    chez
    0.07
    Activations Density 0.011%

    No Known Activations