© 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. 73915
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

    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
    ucci
    -0.08
    point
    -0.07
    party
    -0.07
    rada
    -0.07
    page
    -0.06
    nun
    -0.06
    ye
    -0.06
    pet
    -0.06
     otherwise
    -0.06
    ElementsBy
    -0.06
    POSITIVE LOGITS
    indrical
    0.11
    osate
    0.10
    thag
    0.10
    posium
    0.09
    dney
    0.09
     nhiên
    0.09
    ically
    0.09
    soever
    0.09
    ssa
    0.08
    racuse
    0.08
    Activations Density 0.058%

    No Known Activations