© 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. 69571
    Prev
    Next
    INDEX
    Explanations

    negative constructions or phrases indicating absence or lack

    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
    dp
    -0.05
    arden
    -0.05
    781
    -0.05
    finalize
    -0.05
     bew
    -0.05
    åĢ
    -0.05
    het
    -0.05
    ali
    -0.05
     Ting
    -0.05
    ettes
    -0.05
    POSITIVE LOGITS
    ,readonly
    0.08
    asley
    0.08
    593
    0.08
    ÑĢаг
    0.07
    _TBL
    0.07
    .Immutable
    0.07
    PCODE
    0.07
    icia
    0.07
    ocator
    0.07
    kont
    0.07
    Activations Density 0.008%

    No Known Activations