© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125258
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fool" and its derivatives

    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
    lations
    -0.08
    elli
    -0.07
    ello
    -0.07
    Enlarge
    -0.07
     Pir
    -0.07
     лак
    -0.07
    grupo
    -0.07
    points
    -0.07
    etta
    -0.06
    lain
    -0.06
    POSITIVE LOGITS
    ishly
    0.08
    rush
    0.08
    fo
    0.08
    hard
    0.07
    beg
    0.07
     rush
    0.07
    ery
    0.07
    ish
    0.07
    les
    0.07
    108
    0.06
    Activations Density 0.004%

    No Known Activations