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. 44036
    Prev
    Next
    INDEX
    Explanations

    specific sequences related to online media or image links

    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
    t
    -0.29
    ts
    -0.27
    ta
    -0.26
    ted
    -0.26
    ten
    -0.25
    ting
    -0.25
    ton
    -0.25
    ty
    -0.25
    ti
    -0.24
    tin
    -0.24
    POSITIVE LOGITS
    s
    0.15
    sing
    0.11
    oftware
    0.10
    sar
    0.10
    sse
    0.10
    sak
    0.10
    sou
    0.10
    sed
    0.10
    sword
    0.10
    sage
    0.10
    Activations Density 0.075%

    No Known Activations