© 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. 105888
    Prev
    Next
    INDEX
    Explanations

    phrases related to application processes and fees

    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
     jot
    -0.07
    utherford
    -0.07
    bet
    -0.06
    udos
    -0.06
    (ed
    -0.06
    GBP
    -0.06
    .Attributes
    -0.06
    izes
    -0.06
    ãĥ³ãĤ°
    -0.06
    oot
    -0.06
    POSITIVE LOGITS
    erli
    0.07
    TERN
    0.07
    errick
    0.06
    kili
    0.06
     Colon
    0.06
    ÑĢи
    0.06
    teki
    0.06
    .MixedReality
    0.06
    .PropTypes
    0.06
     gezocht
    0.06
    Activations Density 0.036%

    No Known Activations