© 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. 84253
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions of saving or acquiring digital content

    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
     yacc
    -0.07
    ewear
    -0.07
    etÃŃ
    -0.07
     Lamb
    -0.07
     bend
    -0.06
     Said
    -0.06
    utenberg
    -0.06
    Ïĥμ
    -0.06
    blr
    -0.06
    öm
    -0.06
    POSITIVE LOGITS
    <Guid
    0.07
    143
    0.07
     other
    0.07
    imag
    0.07
    ATUS
    0.07
    £i
    0.07
    823
    0.06
    Assert
    0.06
    ìĬ´
    0.06
    745
    0.06
    Activations Density 0.000%

    No Known Activations