© 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. 107568
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases that indicate actions or plans

    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
    лаз
    -0.06
     beck
    -0.06
    adero
    -0.06
     Cumhur
    -0.06
    edImage
    -0.06
    laughter
    -0.06
    elle
    -0.06
    obao
    -0.06
    txn
    -0.06
    essaging
    -0.06
    POSITIVE LOGITS
    orro
    0.07
    avana
    0.06
    ¸ı
    0.06
    vrier
    0.06
    ynom
    0.06
     your
    0.06
     get
    0.06
    ertype
    0.06
    efa
    0.06
    ĮĢ
    0.06
    Activations Density 0.012%

    No Known Activations