© 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. 125831
    Prev
    Next
    INDEX
    Explanations

    references to financial influence and corruption in politics

    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
    onth
    -0.07
    prak
    -0.07
     peg
    -0.07
    gram
    -0.07
    ius
    -0.06
    itr
    -0.06
    à¸Ľà¸£à¸°
    -0.06
    raman
    -0.06
    usra
    -0.06
    æ³¢
    -0.06
    POSITIVE LOGITS
    unks
    0.07
     influence
    0.07
     Influ
    0.06
    iesel
    0.06
     Influence
    0.06
     Bought
    0.06
    à¹Ĥà¸Ļ
    0.06
    çĮĽ
    0.06
    aws
    0.06
     Neo
    0.06
    Activations Density 0.027%

    No Known Activations