© 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. 104408
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts indicating quantity or the presence of multiple items

    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
    hap
    -0.06
     Knock
    -0.06
    HAV
    -0.06
     Dek
    -0.06
     Rabbit
    -0.05
    anela
    -0.05
    adb
    -0.05
    æIJŃ
    -0.05
     Kennedy
    -0.05
     stav
    -0.05
    POSITIVE LOGITS
    laz
    0.07
    .Encode
    0.07
    beh
    0.07
    /renderer
    0.07
    LIK
    0.07
    ednou
    0.07
    acs
    0.07
    Ñıн
    0.07
    eor
    0.07
    _FP
    0.07
    Activations Density 0.009%

    No Known Activations