© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96372
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    _INITIALIZER
    -0.08
    CEPT
    -0.07
    axter
    -0.07
    lesen
    -0.07
    .DropTable
    -0.07
    елиÑĩ
    -0.07
    زا
    -0.07
    egas
    -0.07
    åIJĽ
    -0.07
    eggies
    -0.07
    POSITIVE LOGITS
     Era
    0.06
    á»ķi
    0.06
    -era
    0.06
    ical
    0.06
    acks
    0.06
     Samoa
    0.06
    år
    0.06
    iyel
    0.06
    okia
    0.05
    okino
    0.05
    Activations Density 0.007%

    No Known Activations