© 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. 79454
    Prev
    Next
    INDEX
    Explanations

    statements that express a lack of options or control, as well as discussions of consequences and critical evaluation

    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
     certain
    -0.08
     sometimes
    -0.08
    olit
    -0.07
    ãģĭãģª
    -0.07
    (?
    -0.07
    ë§Į
    -0.07
    sometimes
    -0.07
     depending
    -0.06
     Sometimes
    -0.06
    Sometimes
    -0.06
    POSITIVE LOGITS
     any
    0.20
     anything
    0.19
     ANY
    0.19
    ä»»ä½ķ
    0.18
     anywhere
    0.17
    anything
    0.17
     anybody
    0.15
     Anything
    0.15
     anyone
    0.15
     qualquer
    0.14
    Activations Density 0.124%

    No Known Activations