© 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. 58345
    Prev
    Next
    INDEX
    Explanations

    temporal references to economic data and trends

    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
    (strpos
    -0.07
    getField
    -0.06
     ziy
    -0.06
     gul
    -0.06
    aclass
    -0.06
     hrd
    -0.06
     dawn
    -0.06
    å£
    -0.06
    bou
    -0.06
    ạ
    -0.06
    POSITIVE LOGITS
    okino
    0.07
    ilden
    0.06
    ibling
    0.06
    odel
    0.06
    öm
    0.06
    ysi
    0.06
    über
    0.06
    Periph
    0.06
    erset
    0.06
    lisi
    0.06
    Activations Density 0.014%

    No Known Activations