© 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. 56151
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting the importance of not solely relying on the speaker's claims

    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
    999
    -0.06
     no
    -0.06
    fol
    -0.06
     front
    -0.05
     Stam
    -0.05
    erer
    -0.05
    bard
    -0.05
     false
    -0.05
    ú
    -0.05
    rong
    -0.05
    POSITIVE LOGITS
    alone
    0.09
     trust
    0.09
     alone
    0.09
    Trust
    0.08
    ÙħاÙĨÛĮ
    0.08
     банкÑĥ
    0.08
     Alone
    0.07
    trust
    0.07
     Trust
    0.07
    пов
    0.07
    Activations Density 0.004%

    No Known Activations