© 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. 105083
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "who" and its context around choice and selection

    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
    rlen
    -0.07
    uke
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    erson
    -0.07
    enberg
    -0.07
    akter
    -0.07
    fov
    -0.06
    abela
    -0.06
    osa
    -0.06
    razil
    -0.06
    POSITIVE LOGITS
     Eid
    0.06
    elic
    0.06
     trusted
    0.06
    AMIL
    0.06
     Brake
    0.06
    719
    0.06
     Mick
    0.06
    å®Ī
    0.06
    ENU
    0.05
    advisor
    0.05
    Activations Density 0.007%

    No Known Activations