© 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. 17502
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wife" and related terms

    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
    weg
    -0.09
    ardi
    -0.09
    wert
    -0.07
    neau
    -0.07
    it
    -0.07
     setDescription
    -0.07
    ality
    -0.07
    ay
    -0.06
    ibus
    -0.06
    ists
    -0.06
    POSITIVE LOGITS
    /part
    0.10
    elijke
    0.09
    hood
    0.08
    zilla
    0.08
    -to
    0.07
    grass
    0.06
    agna
    0.06
    347
    0.06
    lessness
    0.06
    's
    0.06
    Activations Density 0.015%

    No Known Activations