Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96126
    Prev
    Next
    INDEX
    Explanations

    occurrences of conditional phrases and settings within procedural contexts

    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
    afari
    -0.07
    arrera
    -0.07
    -sectional
    -0.07
     Göz
    -0.07
    opoulos
    -0.07
     kla
    -0.07
     billig
    -0.07
    anos
    -0.07
     Eudicots
    -0.07
    ContentLoaded
    -0.07
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    0.06
     Barton
    0.06
     especially
    0.06
     Agency
    0.06
     Crab
    0.06
     Burton
    0.06
    otts
    0.06
     hay
    0.06
     kit
    0.06
     when
    0.06
    Activations Density 0.072%

    No Known Activations