© 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. 5071
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their variations

    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
    IfExists
    -0.08
    á»Ļng
    -0.07
    ocop
    -0.07
    essen
    -0.06
    if
    -0.06
    Ậ
    -0.06
     ring
    -0.06
    åĪĬ
    -0.06
    aben
    -0.06
    ties
    -0.06
    POSITIVE LOGITS
    uyo
    0.07
    538
    0.06
    ampa
    0.06
    urse
    0.06
    owitz
    0.06
    borg
    0.06
    HIR
    0.06
    üz
    0.06
    427
    0.06
     groceries
    0.05
    Activations Density 0.003%

    No Known Activations