© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61656
    Prev
    Next
    INDEX
    Explanations

    phrases related to unexpected situations or conditions

    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
     ballot
    -0.06
    äºĪ
    -0.06
     gettext
    -0.06
    .instructions
    -0.06
    .support
    -0.06
    BALL
    -0.06
     æ±
    -0.05
     Rede
    -0.05
    arding
    -0.05
    rhs
    -0.05
    POSITIVE LOGITS
     closing
    0.08
    jsc
    0.07
     Closing
    0.07
     Disorder
    0.07
     leaving
    0.07
    indle
    0.07
     closure
    0.07
    ůst
    0.06
     security
    0.06
    ISCO
    0.06
    Activations Density 0.010%

    No Known Activations