Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44429
    Prev
    Next
    INDEX
    Explanations

    instances of the word "freak" and its variations

    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
    ounder
    -0.08
    phere
    -0.07
    epar
    -0.07
    egt
    -0.06
    ffer
    -0.06
    ippet
    -0.06
    ipsis
    -0.06
    efault
    -0.06
    zet
    -0.06
    elters
    -0.06
    POSITIVE LOGITS
    ishly
    0.20
    ish
    0.16
    show
    0.15
    onom
    0.14
    y
    0.14
    az
    0.13
    shows
    0.13
    ed
    0.12
    in
    0.11
    iest
    0.11
    Activations Density 0.005%

    No Known Activations