© 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. 120177
    Prev
    Next
    INDEX
    Explanations

    occurrences of familial connections or relationships

    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
    amarin
    -0.08
    iman
    -0.07
    ALER
    -0.06
    occo
    -0.06
    aler
    -0.06
    alers
    -0.06
    apa
    -0.06
    eya
    -0.06
    cea
    -0.06
    sters
    -0.06
    POSITIVE LOGITS
     myself
    0.08
     others
    0.08
     other
    0.07
     ******************************************************************************↵
    0.07
     Wed
    0.07
    Uvs
    0.07
     boon
    0.07
    Slf
    0.06
    IFn
    0.06
    lessness
    0.06
    Activations Density 0.014%

    No Known Activations