© 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. 82617
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the beginning of a story or narrative

    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
    isoft
    -0.07
     Meat
    -0.07
    uchen
    -0.07
    amel
    -0.07
    lev
    -0.06
    obot
    -0.06
    baugh
    -0.06
    amilia
    -0.06
    rouch
    -0.06
     Rosenstein
    -0.06
    POSITIVE LOGITS
     humble
    0.07
     when
    0.07
    tplib
    0.07
    cede
    0.06
    when
    0.06
     acompan
    0.06
    789
    0.06
    582
    0.06
    ANGER
    0.06
     with
    0.06
    Activations Density 0.013%

    No Known Activations