© 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. 129403
    Prev
    Next
    INDEX
    Explanations

    pronouns and words related to addressing the audience or recipients

    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
    gt
    -0.06
    ű
    -0.06
    105
    -0.06
    ÑĢог
    -0.06
    isci
    -0.06
    AAAAAAAA
    -0.06
    ÑĢож
    -0.05
     grö
    -0.05
     dela
    -0.05
    atism
    -0.05
    POSITIVE LOGITS
     with
    0.13
    with
    0.12
    WithData
    0.11
     avec
    0.10
    	with
    0.10
    ewith
    0.10
     vỼi
    0.10
     dengan
    0.10
     withObject
    0.09
     withString
    0.09
    Activations Density 0.041%

    No Known Activations