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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 91901
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly parentheses and brackets

    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
    s
    -0.41
    Ùĩ
    -0.22
    ska
    -0.17
    sburg
    -0.15
    sar
    -0.14
    a
    -0.14
    sian
    -0.13
    sing
    -0.13
    sik
    -0.13
    sand
    -0.13
    POSITIVE LOGITS
    odore
    0.15
    atre
    0.14
    etheless
    0.12
    ÑįÑĤомÑĥ
    0.12
    adays
    0.10
    دÙĪاج
    0.10
    bsites
    0.10
    imately
    0.10
    tlement
    0.10
    gether
    0.09
    Activations Density 0.155%

    No Known Activations