© 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. 15-LLAMASCOPE-RES-131K
    11. 956
    Prev
    Next
    INDEX
    Explanations

    references to individuals in positions of former authority or leadership

    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
    gaard
    -0.07
    BOARD
    -0.07
    ÙĨز
    -0.07
    mey
    -0.06
    loquent
    -0.06
    amt
    -0.06
    ella
    -0.06
    ParseException
    -0.06
    ius
    -0.06
    speech
    -0.06
    POSITIVE LOGITS
    åĽ
    0.06
    iola
    0.06
    Stra
    0.06
     acting
    0.06
    oeff
    0.06
    ácil
    0.05
    /current
    0.05
    -*-
    0.05
     consolidated
    0.05
    Bill
    0.05
    Activations Density 0.006%

    No Known Activations