© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39957
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "review" and its variations, indicating a focus on critiques or evaluations

    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
    owing
    -0.07
    gow
    -0.07
    cola
    -0.07
    uraa
    -0.07
    obo
    -0.07
    kan
    -0.07
    abyrin
    -0.07
    vince
    -0.07
    ura
    -0.06
    arr
    -0.06
    POSITIVE LOGITS
    able
    0.10
    ables
    0.09
    OrCreate
    0.08
    ers
    0.08
    ees
    0.08
    /comment
    0.08
    ãĥ¥
    0.08
    ing
    0.07
    edList
    0.07
    ovacÃŃ
    0.07
    Activations Density 0.028%

    No Known Activations