© 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. 9-LLAMASCOPE-RES-131K
    11. 97778
    Prev
    Next
    INDEX
    Explanations

    phrases related to existence and occurrence

    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
    visa
    -0.07
    uentes
    -0.07
    [".
    -0.07
    Ú¯ÛĮر
    -0.07
    962
    -0.07
     çŁ³
    -0.07
    INED
    -0.06
    åĩºçīĪ
    -0.06
    çŁ³
    -0.06
    odÃŃ
    -0.06
    POSITIVE LOGITS
    alic
    0.06
    arer
    0.06
    PF
    0.06
    achat
    0.06
    IDA
    0.06
    udo
    0.06
    pf
    0.06
    ppe
    0.06
    chn
    0.06
    rico
    0.06
    Activations Density 0.089%

    No Known Activations