© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 40975
    Prev
    Next
    INDEX
    Explanations

    emotional adjectives describing complex situations

    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
    chter
    -0.07
    edis
    -0.07
     пÑĥÑĤем
    -0.07
    ait
    -0.06
    982
    -0.06
    rac
    -0.06
    eson
    -0.06
    Ī¬
    -0.06
    амп
    -0.06
    plementation
    -0.06
    POSITIVE LOGITS
     considering
    0.09
     indeed
    0.08
    ingly
    0.07
     itself
    0.07
    ipop
    0.07
     partly
    0.07
    pecially
    0.06
    ÑıÑĤ
    0.06
     given
    0.06
    oldt
    0.06
    Activations Density 0.029%

    No Known Activations