© 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. 70394
    Prev
    Next
    INDEX
    Explanations

    discussions about perspectives and views in relation to cultural or societal issues

    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
    lsi
    -0.08
    oste
    -0.07
    avor
    -0.07
    kke
    -0.07
    llen
    -0.07
    obia
    -0.07
    awl
    -0.07
    ÄIJT
    -0.07
     done
    -0.07
    edy
    -0.07
    POSITIVE LOGITS
     opinions
    0.10
     opinion
    0.08
     expressed
    0.07
    Express
    0.07
     input
    0.07
    express
    0.07
     express
    0.07
     views
    0.07
     opin
    0.07
    cent
    0.07
    Activations Density 0.033%

    No Known Activations