© 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. 42292
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional distress and desire for change

    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
    ovit
    -0.08
    .statusText
    -0.08
    ovice
    -0.07
     Aux
    -0.07
     aux
    -0.07
    епÑĤи
    -0.07
    wap
    -0.06
    ublish
    -0.06
    usher
    -0.06
    åįĺ
    -0.06
    POSITIVE LOGITS
    anova
    0.06
    hle
    0.06
     Nicholson
    0.06
     istiyorum
    0.06
     fucking
    0.06
    ê°¤
    0.06
    utin
    0.06
    .scalablytyped
    0.06
    angers
    0.06
    ÃŃch
    0.06
    Activations Density 0.004%

    No Known Activations