© 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. 3324
    Prev
    Next
    INDEX
    Explanations

    instances of the word "after" indicating a sequence of events or actions

    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
    ÙĪÙĦÙĪ
    -0.07
    unde
    -0.07
    wright
    -0.07
    avenport
    -0.07
    reira
    -0.06
     Rolled
    -0.06
    $__
    -0.06
    ubat
    -0.06
    اÙģت
    -0.06
     Holl
    -0.06
    POSITIVE LOGITS
    acci
    0.06
    ertura
    0.06
    élé
    0.06
    _iface
    0.06
    Facing
    0.06
    lesh
    0.06
    unning
    0.06
     att
    0.06
    luet
    0.06
    oons
    0.06
    Activations Density 0.019%

    No Known Activations