© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75235
    Prev
    Next
    INDEX
    Explanations

    topics related to high-profile individuals involved in controversial events

    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
    amus
    -0.07
     Kaiser
    -0.06
    addock
    -0.06
    (Py
    -0.06
    ãĥ¼ãĥĩ
    -0.06
    PK
    -0.06
     attribution
    -0.06
    _procs
    -0.06
    vod
    -0.06
     Py
    -0.06
    POSITIVE LOGITS
     Miami
    0.07
     Bond
    0.07
     bond
    0.06
     Nass
    0.06
     ske
    0.06
    .graph
    0.06
    bond
    0.06
    çIJ´
    0.06
    Miami
    0.06
    nez
    0.06
    Activations Density 0.003%

    No Known Activations