© 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. 15-LLAMASCOPE-RES-131K
    6. 62022
    Prev
    Next
    INDEX
    Explanations

    transactions or actions related to organizational decisions and announcements

    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
    UA
    -0.07
    vant
    -0.06
    avin
    -0.06
    acker
    -0.06
     loft
    -0.06
    aben
    -0.06
    大人
    -0.06
    รà¸Ķ
    -0.06
    adder
    -0.06
    RAFT
    -0.06
    POSITIVE LOGITS
    athing
    0.07
     Graves
    0.06
    aurus
    0.06
    auer
    0.06
    itsu
    0.06
    ingen
    0.06
    blah
    0.06
    oping
    0.06
    342
    0.06
    ieves
    0.06
    Activations Density 0.022%

    No Known Activations