© 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. 5417
    Prev
    Next
    INDEX
    Explanations

    key plot points related to character redemption in stories

    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
    aign
    -0.07
     Kami
    -0.07
     kê
    -0.06
     divisible
    -0.06
    329
    -0.06
    istory
    -0.06
    çģ
    -0.06
    leep
    -0.06
     kém
    -0.06
    rech
    -0.06
    POSITIVE LOGITS
     final
    0.14
     finally
    0.13
     Finally
    0.10
     Final
    0.10
    final
    0.09
    Finally
    0.09
    (final
    0.09
    _final
    0.08
     FINAL
    0.08
     cuá»iji
    0.08
    Activations Density 0.028%

    No Known Activations