© 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. 72076
    Prev
    Next
    INDEX
    Explanations

    future expressions and indicators of anticipation or planning

    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
    _MR
    -0.07
     universally
    -0.06
    itude
    -0.06
    ycz
    -0.06
    ixo
    -0.06
    ÑĢез
    -0.06
    %i
    -0.06
    haf
    -0.06
    ypad
    -0.06
    hospital
    -0.06
    POSITIVE LOGITS
    ĥ
    0.06
    >NN
    0.06
    sehen
    0.06
    cus
    0.06
    inand
    0.06
     total
    0.06
    ocs
    0.06
     probably
    0.06
     nice
    0.05
    ozÃŃ
    0.05
    Activations Density 0.031%

    No Known Activations