© 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. 2299
    Prev
    Next
    INDEX
    Explanations

    expressions related to caution and attentiveness

    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
     PE
    -0.06
    loy
    -0.06
    cord
    -0.06
     loc
    -0.06
    emo
    -0.06
    xc
    -0.05
    wed
    -0.05
    quare
    -0.05
     wed
    -0.05
    oner
    -0.05
    POSITIVE LOGITS
     carefully
    0.10
     careful
    0.08
    curacy
    0.08
    fol
    0.07
    æħİ
    0.07
    placement
    0.07
     æħ
    0.07
    vider
    0.07
    abyrinth
    0.07
    oins
    0.07
    Activations Density 0.030%

    No Known Activations