© 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. 9-LLAMASCOPE-RES-131K
    11. 97742
    Prev
    Next
    INDEX
    Explanations

    negation or words that express a lack of something

    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
    rien
    -0.07
    uml
    -0.07
    RG
    -0.07
    lap
    -0.07
     Trev
    -0.06
    weak
    -0.06
    plusplus
    -0.06
     weakened
    -0.06
     weak
    -0.06
    uthor
    -0.06
    POSITIVE LOGITS
    ahlen
    0.07
     victim
    0.07
     Victim
    0.07
    uzzi
    0.07
    _bound
    0.07
    hawks
    0.06
    _pcm
    0.06
     victims
    0.06
     Bound
    0.06
    victim
    0.06
    Activations Density 0.078%

    No Known Activations