© 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 EvalsExportsinterp-engineNEWAPI 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. 92662
    Prev
    Next
    INDEX
    Explanations

    phrases that express an inability or difficulty in calling for help

    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
    .dateFormat
    -0.08
    ninger
    -0.07
    peare
    -0.07
    emachine
    -0.07
    atore
    -0.07
    umpt
    -0.07
    llu
    -0.07
    ër
    -0.07
    idente
    -0.06
     grief
    -0.06
    POSITIVE LOGITS
     escape
    0.10
     Escape
    0.08
     escapes
    0.08
    escape
    0.08
    Escape
    0.07
     Appeal
    0.07
     appeal
    0.07
     escaping
    0.07
    oyal
    0.07
     getaway
    0.07
    Activations Density 0.028%

    No Known Activations