© 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. 116850
    Prev
    Next
    INDEX
    Explanations

    numeric quantities and their associations

    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
    egra
    -0.07
    vara
    -0.07
    rif
    -0.06
    SWG
    -0.06
    ANCED
    -0.06
    .navigationItem
    -0.06
    ledged
    -0.06
    icolon
    -0.06
    å¼ı
    -0.06
    373
    -0.06
    POSITIVE LOGITS
     countries
    0.11
    countries
    0.08
     Countries
    0.08
     paÃŃses
    0.07
    _countries
    0.07
     zemÃŃ
    0.07
     areas
    0.07
     country
    0.07
     counties
    0.06
    Countries
    0.06
    Activations Density 0.007%

    No Known Activations