© 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. 17-LLAMASCOPE-RES-131K
    11. 77452
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative forms of the word "good."

    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
    ãĤ¤ãĥ³ãĥĪ
    -0.06
    alah
    -0.06
    Lazy
    -0.06
    utory
    -0.06
     Lazy
    -0.06
    ersion
    -0.06
    .Interop
    -0.06
    uml
    -0.06
    rades
    -0.06
     Darling
    -0.06
    POSITIVE LOGITS
     way
    0.07
    idge
    0.07
    اث
    0.06
    ãģ«ãģ¨
    0.06
    bay
    0.06
     stay
    0.06
    &M
    0.06
    ymm
    0.06
     addCriterion
    0.06
     Stick
    0.06
    Activations Density 0.008%

    No Known Activations