© 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. 17-LLAMASCOPE-RES-131K
    11. 29243
    Prev
    Next
    INDEX
    Explanations

    declarative statements about personal beliefs or experiences

    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
    ictim
    -0.07
     lá»ĩ
    -0.07
    åĨµ
    -0.07
    inh
    -0.07
    bud
    -0.06
    iah
    -0.06
     Bethlehem
    -0.06
    LocalizedMessage
    -0.06
    phis
    -0.06
    éri
    -0.06
    POSITIVE LOGITS
    .mu
    0.06
    õi
    0.06
     Reyn
    0.06
    ableViewController
    0.06
    aight
    0.06
    Cube
    0.06
    bigint
    0.06
     stage
    0.06
     Cong
    0.05
    sock
    0.05
    Activations Density 0.003%

    No Known Activations