© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97181
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "how to" related to providing guidance or instructions

    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
    istrate
    -0.07
    iment
    -0.07
    tement
    -0.07
    istrov
    -0.07
    iming
    -0.07
    stered
    -0.07
    antee
    -0.06
    presso
    -0.06
    ÑĢеж
    -0.06
    discard
    -0.06
    POSITIVE LOGITS
    769
    0.06
     __("
    0.06
    ERSHEY
    0.06
    enet
    0.06
    omanip
    0.06
     Pend
    0.06
     Lone
    0.06
    vens
    0.06
    Pi
    0.06
    oker
    0.06
    Activations Density 0.008%

    No Known Activations