© 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 EvalsExportsinterp-engineNEWAPI 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. 79792
    Prev
    Next
    INDEX
    Explanations

    references to young individuals and their involvement in various 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
    ̣
    -0.10
    zheimer
    -0.07
    ixo
    -0.07
    ADING
    -0.07
    Ðĩ
    -0.07
    elic
    -0.07
    ampp
    -0.07
    lessly
    -0.07
    ouden
    -0.07
    anse
    -0.07
    POSITIVE LOGITS
     themselves
    0.08
    们
    0.07
    -parent
    0.06
    acket
    0.06
    ths
    0.06
    åĢij
    0.06
    -led
    0.06
    orb
    0.06
    irs
    0.06
     people
    0.05
    Activations Density 0.010%

    No Known Activations