© 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. 2998
    Prev
    Next
    INDEX
    Explanations

    words related to suspicion and suspecting

    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
    .navigator
    -0.08
    ertz
    -0.07
    ucha
    -0.07
    езда
    -0.07
    utz
    -0.07
    views
    -0.07
    enen
    -0.07
    eron
    -0.07
    BorderStyle
    -0.07
    igham
    -0.07
    POSITIVE LOGITS
    ively
    0.10
    ably
    0.08
    ive
    0.08
     Baum
    0.07
    ible
    0.07
    ors
    0.06
    630
    0.06
    aroo
    0.06
     ÏĮÏĦι
    0.06
    oshi
    0.06
    Activations Density 0.010%

    No Known Activations