© 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. 83163
    Prev
    Next
    INDEX
    Explanations

    phrases that express authenticity or truthfulness

    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
    resh
    -0.07
    éĥİ
    -0.06
    bsite
    -0.06
    uo
    -0.06
    ode
    -0.06
    иÑĢÑĥ
    -0.06
    563
    -0.06
    ÙĪراÙĨ
    -0.06
    ÏģιÏĥ
    -0.06
    .blob
    -0.06
    POSITIVE LOGITS
     nature
    0.08
    ì¶Ķ
    0.07
    .TRUE
    0.07
    worthy
    0.07
    à¹ĥà¸Ī
    0.07
    amente
    0.07
    óc
    0.07
    true
    0.07
     true
    0.07
    ourcem
    0.07
    Activations Density 0.003%

    No Known Activations