© 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. 73189
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, particularly names

    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
    erin
    -0.08
    /close
    -0.07
    idge
    -0.07
    tainment
    -0.07
    eration
    -0.07
    ateur
    -0.07
    itat
    -0.07
    aire
    -0.06
    er
    -0.06
    oit
    -0.06
    POSITIVE LOGITS
    onen
    0.08
    elt
    0.07
    itsu
    0.07
    emann
    0.07
    agle
    0.07
    ammers
    0.06
    artz
    0.06
    vironment
    0.06
    forcements
    0.06
    rich
    0.06
    Activations Density 0.003%

    No Known Activations