© 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. 72001
    Prev
    Next
    INDEX
    Explanations

    assertions about credibility and authority

    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
     dek
    -0.07
     flo
    -0.07
    ooter
    -0.06
    Relations
    -0.06
    assa
    -0.06
    رÛĮÙħ
    -0.06
    dek
    -0.06
    foy
    -0.06
    onica
    -0.06
    FTA
    -0.06
    POSITIVE LOGITS
     expertise
    0.12
     authority
    0.12
    expert
    0.11
    authority
    0.11
     Authority
    0.10
    Expert
    0.09
     expert
    0.09
     authorities
    0.09
    Authority
    0.08
     qualifications
    0.08
    Activations Density 0.026%

    No Known Activations