© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56681
    Prev
    Next
    INDEX
    Explanations

    negative connotations or references to "bad" in various contexts

    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
    dale
    -0.08
    tape
    -0.07
    ized
    -0.06
    -vous
    -0.06
    andum
    -0.06
    mino
    -0.06
    laz
    -0.06
    838
    -0.06
    endon
    -0.06
    obia
    -0.06
    POSITIVE LOGITS
    ger
    0.13
    dest
    0.09
    GER
    0.09
    .gdx
    0.08
    -news
    0.08
    gers
    0.08
     luck
    0.08
    vertisement
    0.08
    dddd
    0.08
     Samar
    0.07
    Activations Density 0.015%

    No Known Activations