© 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. 94078
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of."

    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
    ting
    -0.08
    consistent
    -0.07
    amina
    -0.07
     bunch
    -0.07
    ittel
    -0.07
    loor
    -0.06
    patch
    -0.06
    loo
    -0.06
    owski
    -0.06
    berger
    -0.06
    POSITIVE LOGITS
     people
    0.10
     times
    0.07
    rowning
    0.06
    UFFIX
    0.06
    ailles
    0.06
    KeyPress
    0.06
    bet
    0.06
    orks
    0.06
    people
    0.06
    ick
    0.06
    Activations Density 0.023%

    No Known Activations