© 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. 107685
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions within family 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
     Trident
    -0.07
    à¹ĩà¸Ķ
    -0.07
    olley
    -0.06
     Married
    -0.06
    TRL
    -0.06
     Bis
    -0.06
     Mus
    -0.06
    grass
    -0.06
     weddings
    -0.06
    elfare
    -0.06
    POSITIVE LOGITS
     bond
    0.13
     bonding
    0.11
    bond
    0.11
     Bond
    0.11
     together
    0.10
     shared
    0.09
     bonds
    0.09
    åħ±
    0.09
    Bond
    0.09
     åħ±
    0.09
    Activations Density 0.072%

    No Known Activations