© 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 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. 78467
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs indicating actions or outcomes

    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
     cÃłng
    -0.08
    herits
    -0.08
     konkrét
    -0.08
    INVAL
    -0.08
    uhl
    -0.07
    ãģ¾ãĤĬ
    -0.07
     PROGMEM
    -0.07
    qli
    -0.07
    IVATE
    -0.07
    .GraphicsUnit
    -0.07
    POSITIVE LOGITS
     warrant
    0.08
     tr
    0.07
    0.07
     notice
    0.07
     merit
    0.07
     decent
    0.06
     occasionally
    0.06
     reasonably
    0.06
     comfortably
    0.06
    riv
    0.06
    Activations Density 0.027%

    No Known Activations