© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 98520
    Prev
    Next
    INDEX
    Explanations

    numerical data related to editions or printings

    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
    anders
    -0.07
    jad
    -0.06
    avana
    -0.06
    igor
    -0.06
    il
    -0.06
    ar
    -0.06
    warn
    -0.06
    attachment
    -0.06
    attachments
    -0.06
    nnen
    -0.06
    POSITIVE LOGITS
    ì¹ĺ
    0.07
    ì¹ĺëĬĶ
    0.07
    .ribbon
    0.07
    ãĥIJãĤ¤
    0.07
     CDDL
    0.07
    ONSE
    0.07
    .VideoCapture
    0.06
    iddi
    0.06
    .IContainer
    0.06
    ABCDE
    0.06
    Activations Density 0.001%

    No Known Activations