© 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. 118453
    Prev
    Next
    INDEX
    Explanations

    statements and factual claims introduced by the word "according."

    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
     tắt
    -0.08
    erties
    -0.08
     nÃło
    -0.07
    tings
    -0.07
    iversary
    -0.07
    PLIT
    -0.07
    اÙĨÙĩ
    -0.07
    boat
    -0.07
    urd
    -0.07
    intColor
    -0.07
    POSITIVE LOGITS
    er
    0.13
    ly
    0.13
    ed
    0.12
    edir
    0.10
    æĸ¼
    0.10
    e
    0.09
    i
    0.09
    al
    0.08
    a
    0.08
    äºİ
    0.08
    Activations Density 0.020%

    No Known Activations