© 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. 5241
    Prev
    Next
    INDEX
    Explanations

    questions and considerations about obstacles and requirements in various contexts

    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
    luv
    -0.08
    iets
    -0.07
    ceb
    -0.07
    nelle
    -0.07
    atel
    -0.07
    USES
    -0.07
    iard
    -0.07
    iag
    -0.07
    oxide
    -0.07
    aturated
    -0.07
    POSITIVE LOGITS
     need
    0.06
    ordan
    0.06
     alternate
    0.06
     needed
    0.06
    ucz
    0.06
    çİ°
    0.06
     Axe
    0.05
    alternate
    0.05
    uez
    0.05
    .unique
    0.05
    Activations Density 0.007%

    No Known Activations