© 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. 116944
    Prev
    Next
    INDEX
    Explanations

    concepts related to ownership and personal investments

    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
    Insensitive
    -0.06
    ology
    -0.06
    ãĤ¤ãĥ«
    -0.06
    acia
    -0.06
    im
    -0.06
    legg
    -0.06
    -sdk
    -0.06
    099
    -0.06
     prot
    -0.06
    ivery
    -0.06
    POSITIVE LOGITS
    rar
    0.08
    WithOptions
    0.07
    .synthetic
    0.07
    565
    0.07
    gil
    0.07
    FUN
    0.06
     Angiospermae
    0.06
    ubyte
    0.06
     iParam
    0.06
    QUIRED
    0.06
    Activations Density 0.035%

    No Known Activations