© 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. 5-LLAMASCOPE-RES-131K
    11. 126931
    Prev
    Next
    INDEX
    Explanations

    affirmative assertions or statements of agreement

    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
    o
    -0.06
    aliz
    -0.06
    ober
    -0.06
    able
    -0.05
    esk
    -0.05
    eft
    -0.05
    ej
    -0.05
    THEN
    -0.05
    ardin
    -0.05
     eas
    -0.05
    POSITIVE LOGITS
    681
    0.08
    .bunifuFlatButton
    0.08
    UDO
    0.08
    -Sah
    0.07
     itemprop
    0.07
    udo
    0.07
     RuntimeObject
    0.07
    iao
    0.07
    ernel
    0.07
    άνι
    0.07
    Activations Density 0.002%

    No Known Activations