© 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. 15-LLAMASCOPE-RES-131K
    11. 87286
    Prev
    Next
    INDEX
    Explanations

    phrases indicating familial or close 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
    ży
    -0.08
    agrams
    -0.07
    STANCE
    -0.07
    anou
    -0.07
    antal
    -0.07
    ForObject
    -0.07
    rror
    -0.07
    RuntimeObject
    -0.07
    lette
    -0.07
    ongyang
    -0.07
    POSITIVE LOGITS
     accompanying
    0.08
     accompanied
    0.08
     accompany
    0.07
    اÙĨÙĩ
    0.07
     accompagn
    0.07
     ÑģопÑĢов
    0.07
     accompanies
    0.06
     belongings
    0.06
     acompañ
    0.06
     ÙĩÙħراÙĩ
    0.06
    Activations Density 0.026%

    No Known Activations