© 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. 93028
    Prev
    Next
    INDEX
    Explanations

    negative phrases or sentiments regarding recognition and representation

    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
    usch
    -0.06
    isable
    -0.06
    elts
    -0.06
    iac
    -0.06
    "./
    -0.06
    ziel
    -0.06
    undi
    -0.06
    ron
    -0.06
    ruk
    -0.06
    508
    -0.06
    POSITIVE LOGITS
     properly
    0.08
    eries
    0.08
    proper
    0.08
     awareness
    0.08
     adequately
    0.07
    éĤª
    0.07
     Proper
    0.07
     fully
    0.07
     attention
    0.07
    attention
    0.07
    Activations Density 0.087%

    No Known Activations