© 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. 81125
    Prev
    Next
    INDEX
    Explanations

    phrases related to careful reading and understanding of documents 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
     yiy
    -0.06
    ?q
    -0.06
    кÑĥп
    -0.06
    ··
    -0.06
     gente
    -0.06
     guerr
    -0.06
    dna
    -0.06
    þ
    -0.06
    hap
    -0.06
     kaydet
    -0.06
    POSITIVE LOGITS
     foregoing
    0.08
    inea
    0.08
    SED
    0.07
    ละ
    0.07
    ä¸Ķ
    0.07
    sel
    0.06
    енно
    0.06
    itemid
    0.06
    rex
    0.06
    xoops
    0.06
    Activations Density 0.002%

    No Known Activations