© 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. 82994
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and the concept of 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
    astle
    -0.07
    rapper
    -0.07
    otre
    -0.07
    ahir
    -0.07
    agy
    -0.07
    ombre
    -0.07
    orrar
    -0.07
    iston
    -0.07
     libertin
    -0.07
    versed
    -0.07
    POSITIVE LOGITS
    anya
    0.06
    /of
    0.06
    /or
    0.06
     young
    0.06
    juana
    0.05
     merc
    0.05
     elder
    0.05
    Validity
    0.05
     Calgary
    0.05
     nearest
    0.05
    Activations Density 0.015%

    No Known Activations