© 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. 18447
    Prev
    Next
    INDEX
    Explanations

    statistics related to economic hardship and poverty levels

    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
    ãĥªãĥ³ãĤ°
    -0.08
     seins
    -0.07
     ÑĨи
    -0.07
    ãĤ¤ãĤ¯
    -0.07
    EMPLARY
    -0.07
    [".
    -0.07
    AFE
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
    ï¼ļ"
    -0.07
    URLException
    -0.07
    POSITIVE LOGITS
    rom
    0.06
    anza
    0.06
    anger
    0.06
    me
    0.06
    ibe
    0.06
    ieg
    0.06
     (
    0.06
    ent
    0.06
     record
    0.05
    dom
    0.05
    Activations Density 0.000%

    No Known Activations