© 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. 15-LLAMASCOPE-RES-131K
    6. 27432
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of refusal and their contexts

    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
    ä¾
    -0.07
    aldi
    -0.07
    Completed
    -0.06
    uyết
    -0.06
    itational
    -0.06
     maximal
    -0.06
    ấp
    -0.06
    ìłĢ
    -0.06
    anical
    -0.06
    aversable
    -0.05
    POSITIVE LOGITS
    apr
    0.07
    .Keyword
    0.07
    egg
    0.06
    msp
    0.06
    _DUMP
    0.06
     RequestOptions
    0.06
    ỡ
    0.06
    Blank
    0.06
    lj
    0.06
    ês
    0.06
    Activations Density 0.017%

    No Known Activations