© 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. 121094
    Prev
    Next
    INDEX
    Explanations

    references to political representatives and legislative assemblies in Italy

    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
    /Instruction
    -0.07
     ($.
    -0.07
    velt
    -0.06
    aleur
    -0.06
    èĭ
    -0.06
    ebek
    -0.06
     è»
    -0.06
     salute
    -0.06
     Nicholson
    -0.05
    ť
    -0.05
    POSITIVE LOGITS
    201
    0.08
    cheon
    0.07
    uckle
    0.07
    202
    0.07
    andon
    0.07
    .bunifuFlatButton
    0.07
    777
    0.06
    antine
    0.06
    ÅĤy
    0.06
    otas
    0.06
    Activations Density 0.002%

    No Known Activations