© 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. 98311
    Prev
    Next
    INDEX
    Explanations

    negative comments directed towards a specific person or group

    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
    mess
    -0.08
    ioc
    -0.07
    NECT
    -0.07
    egie
    -0.07
    psc
    -0.07
    ILLISECONDS
    -0.07
    erdale
    -0.07
     Antar
    -0.07
    acier
    -0.07
    eco
    -0.07
    POSITIVE LOGITS
    ensch
    0.07
    öh
    0.06
    Ĥæķ°
    0.06
    uma
    0.06
    caff
    0.06
     cle
    0.06
    usto
    0.06
    ustral
    0.06
    adoo
    0.06
    Form
    0.06
    Activations Density 0.000%

    No Known Activations