© 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. 95113
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes related to construction and professional fields

    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
    iew
    -0.07
    abwe
    -0.07
    ãĤ±ãĥĥãĥĪ
    -0.07
     Nga
    -0.07
    اث
    -0.07
    flo
    -0.06
    ằng
    -0.06
     hrom
    -0.06
    ér
    -0.06
     _{}
    -0.06
    POSITIVE LOGITS
    ubes
    0.08
    /post
    0.08
    /pre
    0.07
     Ùħباش
    0.07
    /current
    0.07
    ilibrium
    0.07
    «a
    0.06
    andon
    0.06
    .pref
    0.06
    aphael
    0.06
    Activations Density 0.022%

    No Known Activations