© 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. 1728
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating necessity, conditions, and expectations

    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
    anova
    -0.07
     reap
    -0.07
    ibre
    -0.06
     Exped
    -0.06
     wet
    -0.06
    anim
    -0.06
    imos
    -0.06
    uki
    -0.06
    orc
    -0.06
     exped
    -0.06
    POSITIVE LOGITS
    æĤł
    0.08
    ignet
    0.07
    åºŃ
    0.07
     thems
    0.06
    istrovstvÃŃ
    0.06
    .Setter
    0.06
    chwitz
    0.06
     indeed
    0.06
    çīĻ
    0.06
    -Trump
    0.06
    Activations Density 0.102%

    No Known Activations