© 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 EvalsExportsAPI 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. 84402
    Prev
    Next
    INDEX
    Explanations

    instances of emotional or evaluative language related to events or actions

    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
    ationale
    -0.08
     nackte
    -0.07
    itoris
    -0.07
    ylko
    -0.07
    asal
    -0.07
    onga
    -0.07
    екаÑĢ
    -0.07
    edback
    -0.07
     tiener
    -0.07
    hai
    -0.07
    POSITIVE LOGITS
     finally
    0.21
     Lastly
    0.21
    Lastly
    0.20
     Finally
    0.19
    finally
    0.17
    Finally
    0.16
     overall
    0.15
     altogether
    0.14
     Overall
    0.13
     all
    0.13
    Activations Density 0.199%

    No Known Activations