© 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. 15-LLAMASCOPE-RES-131K
    11. 90652
    Prev
    Next
    INDEX
    Explanations

    HTML content and metadata

    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
    ierce
    -0.06
     dope
    -0.06
    acer
    -0.06
     Voll
    -0.06
    sec
    -0.06
    umann
    -0.06
    OUN
    -0.06
    imin
    -0.05
    ounding
    -0.05
    chw
    -0.05
    POSITIVE LOGITS
     Affero
    0.09
    å¼ı
    0.08
    StackNavigator
    0.07
     Strand
    0.07
    خصص
    0.07
    (Target
    0.07
    λικ
    0.07
    -NLS
    0.07
    _REQUIRE
    0.07
    ÏĦÏĮÏĤ
    0.07
    Activations Density 0.000%

    No Known Activations