© 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. 4559
    Prev
    Next
    INDEX
    Explanations

    phrases expressing anticipation or eagerness to assist or connect with someone

    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
     meiden
    -0.07
    .toolbox
    -0.06
    ometr
    -0.06
    оÑĤи
    -0.06
    atcher
    -0.06
    лев
    -0.05
    ॰
    -0.05
    allah
    -0.05
    èm
    -0.05
    jug
    -0.05
    POSITIVE LOGITS
     chance
    0.07
    xca
    0.06
    TEAM
    0.06
    gran
    0.06
     dispens
    0.06
    меÑģÑĤ
    0.06
     TEAM
    0.06
    incr
    0.06
    æ´
    0.06
    isko
    0.06
    Activations Density 0.009%

    No Known Activations