© 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. 87555
    Prev
    Next
    INDEX
    Explanations

    words expressing strong emotions or sentiments

    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
    loor
    -0.07
    avor
    -0.07
    uen
    -0.06
     or
    -0.06
    697
    -0.06
    ureka
    -0.06
     tent
    -0.06
    umba
    -0.06
    onto
    -0.06
    alis
    -0.06
    POSITIVE LOGITS
    Mismatch
    0.06
    DCALL
    0.06
    .readyState
    0.06
    etrize
    0.06
    Meter
    0.06
    екаÑĢ
    0.06
    ¯¿
    0.06
     prostituer
    0.06
    aminer
    0.06
    jah
    0.06
    Activations Density 0.029%

    No Known Activations