© 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. 39363
    Prev
    Next
    INDEX
    Explanations

    terms related to intimacy and personal connections

    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
    igy
    -0.08
    hlas
    -0.08
    Åĵ
    -0.08
    ÄįÃŃ
    -0.08
     kuk
    -0.07
    çīĮ
    -0.07
    nou
    -0.07
    naires
    -0.07
    768
    -0.07
    vez
    -0.07
    POSITIVE LOGITS
    íķĺê²Į
    0.08
     details
    0.08
    /close
    0.08
    /ext
    0.07
    /internal
    0.07
    /private
    0.07
    ELY
    0.07
    /details
    0.06
     enough
    0.06
    /Private
    0.06
    Activations Density 0.004%

    No Known Activations