© 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. 39336
    Prev
    Next
    INDEX
    Explanations

    terms associated with emotional struggles or feelings of frustration

    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
    onde
    -0.07
    ucken
    -0.07
    ustin
    -0.07
    vida
    -0.07
    filer
    -0.07
    _COMPAT
    -0.07
    unci
    -0.06
    forc
    -0.06
    lero
    -0.06
    stood
    -0.06
    POSITIVE LOGITS
     ex
    0.14
    (ex
    0.07
    /ex
    0.07
    .ex
    0.07
    -ex
    0.06
    ex
    0.06
    iled
    0.06
    оÑĩка
    0.06
     exp
    0.06
     leth
    0.06
    Activations Density 0.012%

    No Known Activations