© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125396
    Prev
    Next
    INDEX
    Explanations

    mentions of sheep and their roles or characteristics in various contexts

    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
    usive
    -0.08
    zh
    -0.08
    hw
    -0.07
    eo
    -0.06
    ģn
    -0.06
    cki
    -0.06
     Rat
    -0.06
    cron
    -0.06
    edis
    -0.06
    DDS
    -0.06
    POSITIVE LOGITS
    ishly
    0.10
    skin
    0.09
    /go
    0.08
    shed
    0.07
    oni
    0.07
    meal
    0.07
    skins
    0.07
    hod
    0.06
    assador
    0.06
    her
    0.06
    Activations Density 0.010%

    No Known Activations