© 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. 40363
    Prev
    Next
    INDEX
    Explanations

    concepts related to social hierarchy and class dynamics

    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
    AccessException
    -0.08
    rais
    -0.08
    .scalablytyped
    -0.08
     sond
    -0.08
    esiz
    -0.08
    eln
    -0.08
    deniz
    -0.07
    ych
    -0.07
    uji
    -0.07
    ONT
    -0.07
    POSITIVE LOGITS
     others
    0.08
     ones
    0.08
     Ones
    0.08
     Others
    0.07
     counterpart
    0.07
    isman
    0.07
    others
    0.06
     counterparts
    0.06
     whereas
    0.06
     (
    0.06
    Activations Density 0.074%

    No Known Activations