© 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 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. 9-LLAMASCOPE-RES-131K
    11. 97302
    Prev
    Next
    INDEX
    Explanations

    frequent and common phrases, particularly in conversational or explanatory 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
     Kingdom
    -0.07
    636
    -0.07
     jim
    -0.06
    UX
    -0.06
    ients
    -0.06
     dist
    -0.06
    angers
    -0.06
    stable
    -0.06
    å°ģ
    -0.06
    pig
    -0.06
    POSITIVE LOGITS
    nees
    0.08
    oji
    0.07
    ptune
    0.07
    roker
    0.07
    .IsDBNull
    0.07
    ãĥĥãĤ°
    0.07
    unker
    0.06
    ãĤªãĥª
    0.06
    cala
    0.06
    ptest
    0.06
    Activations Density 0.014%

    No Known Activations