© 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. 94763
    Prev
    Next
    INDEX
    Explanations

    key actions related to managing family dynamics and responsibilities

    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
    rome
    -0.08
    DOG
    -0.07
    ;++
    -0.06
    aph
    -0.06
    idget
    -0.06
    æģ
    -0.06
    ynos
    -0.06
     ì·¨
    -0.06
    rab
    -0.06
    ocab
    -0.06
    POSITIVE LOGITS
     poly
    0.07
    modele
    0.07
    çĿ
    0.07
     amen
    0.06
    ppelin
    0.06
     sche
    0.06
    eload
    0.06
    ROADCAST
    0.06
    experiment
    0.06
    poly
    0.06
    Activations Density 0.000%

    No Known Activations