© 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. 72007
    Prev
    Next
    INDEX
    Explanations

    negative values or themes related to loss or decline

    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
    atica
    -0.06
    EMA
    -0.06
    idges
    -0.06
    èm
    -0.06
    ç±
    -0.06
    continent
    -0.06
    lein
    -0.06
     е
    -0.06
     sweet
    -0.06
     Brewer
    -0.05
    POSITIVE LOGITS
    202
    0.08
    çľ
    0.07
    201
    0.07
    bite
    0.06
    AMP
    0.06
     Conj
    0.06
    argout
    0.06
    <Props
    0.06
    enco
    0.06
    _portal
    0.06
    Activations Density 0.008%

    No Known Activations