© 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. 125579
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and moral introspection

    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
    .joda
    -0.08
    istrovstvÃŃ
    -0.08
    _chip
    -0.07
     suic
    -0.07
    nten
    -0.07
    Ñıз
    -0.07
    _marshall
    -0.07
    каÑģ
    -0.07
    _modifier
    -0.07
    imizer
    -0.07
    POSITIVE LOGITS
     past
    0.13
     previous
    0.10
     mistakes
    0.08
     earlier
    0.08
    past
    0.08
     actions
    0.08
     trans
    0.08
     missed
    0.08
     Previous
    0.07
    Previous
    0.07
    Activations Density 0.036%

    No Known Activations