© 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. 81906
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" and related forms indicating existence or function

    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
    Ỽp
    -0.07
    inou
    -0.07
    lec
    -0.07
    idy
    -0.07
    ekil
    -0.06
    etin
    -0.06
    emez
    -0.06
    eç
    -0.06
    erable
    -0.06
    pace
    -0.06
    POSITIVE LOGITS
     intended
    0.07
    oscope
    0.06
    è´Łè´£
    0.06
    ìļ©
    0.06
    è
    0.06
    سÙĩ
    0.06
    vider
    0.06
    INGLE
    0.06
    amoto
    0.06
     Harm
    0.05
    Activations Density 0.037%

    No Known Activations