© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84093
    Prev
    Next
    INDEX
    Explanations

    instances of the word "meet" and its variations, indicating a focus on gatherings or encounters

    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
    idth
    -0.07
    enheim
    -0.07
    uj
    -0.06
    vette
    -0.06
    udit
    -0.06
    unds
    -0.06
    udad
    -0.06
    евеÑĢ
    -0.06
    /we
    -0.06
    alcon
    -0.06
    POSITIVE LOGITS
    ropolis
    0.13
    tle
    0.10
    ioned
    0.10
    ropolitan
    0.10
    amodel
    0.08
    onym
    0.08
    abolic
    0.07
    ropol
    0.07
     nhau
    0.07
    atars
    0.07
    Activations Density 0.019%

    No Known Activations