© 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. 128002
    Prev
    Next
    INDEX
    Explanations

    phrases related to access and restriction

    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
    cip
    -0.07
    ¹Ħ
    -0.07
    uilder
    -0.07
    aggio
    -0.06
    ossip
    -0.06
    ersed
    -0.06
    .dm
    -0.06
    -san
    -0.06
    CEE
    -0.06
    .AspNet
    -0.06
    POSITIVE LOGITS
    oint
    0.07
     Shut
    0.06
    aga
    0.06
    _shapes
    0.06
    ount
    0.06
     Sham
    0.06
     '\''
    0.06
    oria
    0.06
    503
    0.06
     occasional
    0.06
    Activations Density 0.001%

    No Known Activations