© 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. 79521
    Prev
    Next
    INDEX
    Explanations

    references to communication or interactions with others

    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
    mani
    -0.07
    MES
    -0.06
     accountable
    -0.06
    estar
    -0.06
    _mC
    -0.06
     é»
    -0.06
     Rencontres
    -0.06
    aida
    -0.06
    å°Ĥ
    -0.06
    bots
    -0.06
    POSITIVE LOGITS
     direction
    0.13
    direction
    0.11
     Direction
    0.10
     directions
    0.10
    _direction
    0.09
    æĸ¹åIJij
    0.09
     Directions
    0.09
    Direction
    0.08
    -direction
    0.08
    .direction
    0.08
    Activations Density 0.047%

    No Known Activations