© 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 EvalsExportsAPI 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. 59216
    Prev
    Next
    INDEX
    Explanations

    phrases and references to essential components or qualities within various contexts

    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
    дина
    -0.07
    iete
    -0.06
    ê³
    -0.06
    Å¡lo
    -0.06
     Bor
    -0.06
    lien
    -0.06
    OPY
    -0.06
    opy
    -0.06
    CLE
    -0.06
    osti
    -0.06
    POSITIVE LOGITS
     typical
    0.09
    ntag
    0.08
     Typical
    0.07
    itsu
    0.07
    ucher
    0.07
    acus
    0.07
    stroy
    0.07
    fv
    0.07
    675
    0.07
    ova
    0.07
    Activations Density 0.064%

    No Known Activations