© 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. 30663
    Prev
    Next
    INDEX
    Explanations

    concepts related to definitions and the meaning of identity

    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
    ¿
    -0.07
    amm
    -0.06
    meld
    -0.06
    ivel
    -0.06
     :";↵
    -0.06
    agini
    -0.06
    .DefaultCellStyle
    -0.06
    μÏĨ
    -0.06
    á»įng
    -0.06
    amel
    -0.06
    POSITIVE LOGITS
     definition
    0.08
     Definition
    0.07
     true
    0.07
     definitions
    0.07
    esium
    0.07
    adata
    0.06
    oldem
    0.06
     spas
    0.06
    aire
    0.06
    abis
    0.06
    Activations Density 0.069%

    No Known Activations