© 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. 61858
    Prev
    Next
    INDEX
    Explanations

    phrases containing strong possessive or demonstrative indicators

    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
    pler
    -0.07
    ικο
    -0.07
    tsky
    -0.07
    ozem
    -0.07
     :č↵
    -0.07
    аниÑİ
    -0.07
    ikki
    -0.06
    ikk
    -0.06
    едж
    -0.06
    ikal
    -0.06
    POSITIVE LOGITS
     sense
    0.09
     sure
    0.07
    eil
    0.07
    uman
    0.07
     life
    0.06
     feel
    0.06
    ifference
    0.06
     job
    0.06
    .epam
    0.06
     noises
    0.06
    Activations Density 0.023%

    No Known Activations