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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76605
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future actions or predictions

    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
     Armour
    -0.07
    olib
    -0.06
    ision
    -0.06
    ivé
    -0.06
    aser
    -0.06
    ibi
    -0.06
     Cycle
    -0.06
    Ãło
    -0.06
    .builders
    -0.06
    ãĥ¼ãĥł
    -0.06
    POSITIVE LOGITS
    ulkan
    0.07
    actical
    0.07
    axed
    0.06
     managed
    0.06
    ured
    0.06
    lant
    0.06
     unders
    0.06
    OwnProperty
    0.06
    Axes
    0.06
    BaseContext
    0.06
    Activations Density 0.030%

    No Known Activations