© 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. 85448
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong emotional reactions or evaluations

    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
    elles
    -0.08
    subst
    -0.07
    oot
    -0.07
    aches
    -0.07
    /fw
    -0.06
    foon
    -0.06
     Ware
    -0.06
    ervers
    -0.06
    582
    -0.06
    qing
    -0.06
    POSITIVE LOGITS
     statement
    0.13
    statement
    0.11
     statements
    0.10
     sentiments
    0.08
     sentence
    0.08
    Statement
    0.08
     quoted
    0.07
     Amen
    0.07
     Statement
    0.07
     sentiment
    0.07
    Activations Density 0.078%

    No Known Activations