© 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. 2658
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to the front of objects or locations

    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
    its
    -0.07
    #echo
    -0.07
    ãģŁãĤī
    -0.07
    ovat
    -0.06
    екаÑĢ
    -0.06
    ITS
    -0.06
    çİĩ
    -0.06
    ond
    -0.06
    766
    -0.06
    adiens
    -0.06
    POSITIVE LOGITS
    /front
    0.10
    iers
    0.10
    isp
    0.10
    matter
    0.10
    /back
    0.09
    (front
    0.09
    most
    0.08
    -facing
    0.08
    ière
    0.08
    iere
    0.07
    Activations Density 0.016%

    No Known Activations