© 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. 76978
    Prev
    Next
    INDEX
    Explanations

    terms related to family and household composition

    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
    ohl
    -0.06
    meaning
    -0.06
    uien
    -0.06
    rve
    -0.06
    etto
    -0.06
     ob
    -0.06
    obel
    -0.06
    obic
    -0.06
    .helpers
    -0.05
    elta
    -0.05
    POSITIVE LOGITS
     Cave
    0.07
    peater
    0.07
    rend
    0.07
    inas
    0.07
     baÅŁÄ±na
    0.06
    ooke
    0.06
    ÙĨاÙĨ
    0.06
    ods
    0.06
    HeaderValue
    0.06
    -cent
    0.06
    Activations Density 0.001%

    No Known Activations