© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 99275
    Prev
    Next
    INDEX
    Explanations

    indicative text markers and structural elements of online messages or forums

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    rollo
    -0.06
    ij
    -0.06
    amage
    -0.06
     Ramp
    -0.06
     ring
    -0.06
    ija
    -0.06
    uga
    -0.06
     ramp
    -0.06
     sentiment
    -0.06
    rama
    -0.06
    POSITIVE LOGITS
    âĻ¡
    0.07
    çł²
    0.07
    DisplayStyle
    0.07
    imum
    0.06
    ãĤ¦ãĤ¹
    0.06
    λικ
    0.06
    éijij
    0.06
    รà¸ģ
    0.06
    quin
    0.06
    coder
    0.06
    Activations Density 0.025%

    No Known Activations