© 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. 17-LLAMASCOPE-RES-131K
    11. 41452
    Prev
    Next
    INDEX
    Explanations

    Negation words or phrases expressing 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
    _firestore
    -0.08
    plain
    -0.08
    quam
    -0.07
    oen
    -0.07
    heit
    -0.07
    slt
    -0.07
    plen
    -0.07
    pest
    -0.07
    PCS
    -0.07
    orbit
    -0.07
    POSITIVE LOGITS
    tingham
    0.11
    urnal
    0.09
    ional
    0.08
    withstanding
    0.08
     surprisingly
    0.08
    eworthy
    0.07
    epad
    0.07
    ices
    0.07
    ting
    0.07
    zsche
    0.07
    Activations Density 0.021%

    No Known Activations