© 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. 17865
    Prev
    Next
    INDEX
    Explanations

    autobiographical elements in storytelling

    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
     èIJ
    -0.06
     lent
    -0.05
    æ°
    -0.05
     paraph
    -0.05
    @student
    -0.05
    sov
    -0.05
     Pure
    -0.05
    ng
    -0.05
     volume
    -0.05
     instrumental
    -0.05
    POSITIVE LOGITS
     autobi
    0.19
     personal
    0.15
     autobiography
    0.14
    personal
    0.14
    Personal
    0.13
     Personal
    0.13
    _personal
    0.11
     memoir
    0.11
     osobnÃŃ
    0.10
     лиÑĩ
    0.10
    Activations Density 0.061%

    No Known Activations