© 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. 54693
    Prev
    Next
    INDEX
    Explanations

    references to hidden or undisclosed information

    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
    ãģ¡ãĤĩ
    -0.09
     ìĥĪê¸Ģ
    -0.09
    евиÑĩ
    -0.09
    彦
    -0.08
    Insensitive
    -0.08
    ubern
    -0.08
    ำ
    -0.08
    ÙĦاÙħ
    -0.07
    hone
    -0.07
    lero
    -0.07
    POSITIVE LOGITS
     secrets
    0.11
     secret
    0.09
     Secrets
    0.08
     secre
    0.07
     revealed
    0.07
     about
    0.07
     shared
    0.07
     knowledge
    0.07
     deep
    0.06
     hiding
    0.06
    Activations Density 0.013%

    No Known Activations