© 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. 82888
    Prev
    Next
    INDEX
    Explanations

    instances of specific names or identifiers, particularly related to individuals or entities

    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
    buz
    -0.08
    -lang
    -0.07
    Äħż
    -0.07
    isposable
    -0.07
    NER
    -0.07
    nesc
    -0.07
    opot
    -0.07
    uten
    -0.07
    inou
    -0.07
    ủng
    -0.07
    POSITIVE LOGITS
    cope
    0.07
    aur
    0.07
    issance
    0.06
    ogue
    0.06
    illed
    0.06
    days
    0.06
     Rifle
    0.06
     Ideal
    0.06
    hea
    0.06
    å±ħ
    0.06
    Activations Density 0.041%

    No Known Activations