© 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. 71584
    Prev
    Next
    INDEX
    Explanations

    connections or conjunctions in sentences

    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
    reh
    -0.07
    à¸Ĭม
    -0.06
    abd
    -0.06
     flavored
    -0.06
    usa
    -0.06
    GridColumn
    -0.06
    vÄĽdom
    -0.06
    .ly
    -0.06
    æĻ¶
    -0.06
    rible
    -0.06
    POSITIVE LOGITS
    neau
    0.07
     grub
    0.07
    eb
    0.07
     Äįe
    0.06
    ÏĦÎŃ
    0.06
    profit
    0.06
    sett
    0.06
    wizard
    0.06
    suit
    0.06
     pyl
    0.06
    Activations Density 0.000%

    No Known Activations