© 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. 16534
    Prev
    Next
    INDEX
    Explanations

    terms related to societal and institutional reform

    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
    Enlarge
    -0.06
     drastic
    -0.06
    амеÑĤ
    -0.06
    opoulos
    -0.06
    lep
    -0.06
    879
    -0.06
    stras
    -0.06
    âĢĥ
    -0.05
     tired
    -0.05
    &nbsp
    -0.05
    POSITIVE LOGITS
     BITTE
    0.08
     Erotische
    0.07
    cript
    0.07
    tractive
    0.07
    indow
    0.07
    autiful
    0.07
    ÅĽmy
    0.07
    /Peak
    0.07
    ofday
    0.07
    auth
    0.07
    Activations Density 0.000%

    No Known Activations