© 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. 5411
    Prev
    Next
    INDEX
    Explanations

    punctuation and various forms of emphasis in sentence structures

    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
    uzey
    -0.09
    cé
    -0.09
    ãĥ³ãĤ¹
    -0.08
    áu
    -0.08
    оÑĢд
    -0.08
    .gb
    -0.07
    Ìĥ
    -0.07
    å¨
    -0.07
    oui
    -0.07
    umbn
    -0.07
    POSITIVE LOGITS
     themselves
    0.11
     others
    0.10
     some
    0.08
    others
    0.08
     myself
    0.08
     who
    0.07
     Others
    0.07
    some
    0.07
     me
    0.07
     many
    0.07
    Activations Density 0.086%

    No Known Activations