© 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. 76695
    Prev
    Next
    INDEX
    Explanations

    the word "In" at the beginning of sentences or phrases

    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
    rawn
    -0.06
    ochond
    -0.06
    duct
    -0.06
    stood
    -0.06
    ered
    -0.06
    ducted
    -0.06
    ron
    -0.06
     nowhere
    -0.06
    éric
    -0.06
    aise
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
     pornografia
    0.08
    Argb
    0.07
    getDisplay
    0.07
    /feed
    0.07
    MBER
    0.07
    iele
    0.07
    uat
    0.07
    ãĥ¼ãĥĢ
    0.07
    ","\
    0.06
    Activations Density 0.015%

    No Known Activations