© 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. 3042
    Prev
    Next
    INDEX
    Explanations

    phrases expressing reluctance or refusal

    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
    hw
    -0.07
    маз
    -0.07
    .fun
    -0.06
    etsk
    -0.06
    ITT
    -0.06
    286
    -0.06
     Compass
    -0.06
    ỳ
    -0.06
    bjerg
    -0.06
    à¹īà¸ĩ
    -0.06
    POSITIVE LOGITS
     thank
    0.15
    thank
    0.12
    Thank
    0.12
     Thank
    0.12
    è°¢
    0.10
     THANK
    0.09
     thanks
    0.08
    thanks
    0.08
     Thanks
    0.08
    pref
    0.08
    Activations Density 0.065%

    No Known Activations