© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55639
    Prev
    Next
    INDEX
    Explanations

    color specifications in CSS code

    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
    yleft
    -0.09
     nackte
    -0.08
    amet
    -0.08
    AMY
    -0.07
    typings
    -0.07
    afs
    -0.07
    lobs
    -0.07
    èĬĿ
    -0.07
    frey
    -0.07
    elles
    -0.07
    POSITIVE LOGITS
     Uniform
    0.06
    ÑĸннÑı
    0.06
     Vent
    0.06
    ³
    0.05
    iet
    0.05
     pap
    0.05
    inde
    0.05
    erm
    0.05
     nat
    0.05
     Beit
    0.05
    Activations Density 0.000%

    No Known Activations