© 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. 119748
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and expressions of existence

    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
     Pell
    -0.06
    hawk
    -0.06
    κÎŃ
    -0.06
    piece
    -0.06
    Ñĥж
    -0.05
    acket
    -0.05
    patrick
    -0.05
    ázd
    -0.05
    _pitch
    -0.05
    PCS
    -0.05
    POSITIVE LOGITS
    enberg
    0.08
    nav
    0.08
    afia
    0.07
    LOPT
    0.06
    ither
    0.06
    aken
    0.06
    OLON
    0.06
    à¸Ľà¸£à¸°à¸ª
    0.06
    lam
    0.06
    uraa
    0.06
    Activations Density 0.001%

    No Known Activations