© 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. 77545
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate demand and community engagement

    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
    cola
    -0.06
    Û²Û°Û²
    -0.06
    alli
    -0.06
    ller
    -0.06
    INI
    -0.06
    Äĥr
    -0.06
    ItemAt
    -0.06
    alez
    -0.06
    titleLabel
    -0.06
     Recommendation
    -0.06
    POSITIVE LOGITS
     Demand
    0.10
     demand
    0.10
    Demand
    0.08
     interest
    0.08
     response
    0.08
     Hund
    0.07
     reaction
    0.07
     reactions
    0.07
    Interest
    0.07
    storybook
    0.07
    Activations Density 0.028%

    No Known Activations