© 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. 9-LLAMASCOPE-RES-131K
    11. 97173
    Prev
    Next
    INDEX
    Explanations

    figurative expressions and hyperbolic phrases related to costs and emotional states

    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
    ista
    -0.07
    unga
    -0.06
    tt
    -0.06
    unks
    -0.06
     Guill
    -0.06
    iface
    -0.06
    fi
    -0.06
    artial
    -0.06
    äd
    -0.06
     çĻº
    -0.06
    POSITIVE LOGITS
    shima
    0.07
    ạn
    0.07
    á»ijng
    0.07
    331
    0.06
    nth
    0.06
    agan
    0.06
    SEN
    0.06
    λμ
    0.06
    ả
    0.06
    izik
    0.06
    Activations Density 0.032%

    No Known Activations