© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 95513
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and descriptions related to food and gifts

    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
    _MPI
    -0.07
    ipline
    -0.07
     Fold
    -0.06
    eltas
    -0.06
    DCF
    -0.06
    ÑĢож
    -0.06
    ifen
    -0.06
    tparam
    -0.06
    elta
    -0.06
    .ensure
    -0.06
    POSITIVE LOGITS
    VEC
    0.06
    å¹
    0.06
     dr
    0.06
    uhl
    0.06
    .qual
    0.06
    riter
    0.06
    dek
    0.06
    ¤í
    0.06
     Contents
    0.06
    edly
    0.05
    Activations Density 0.092%

    No Known Activations