© 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. 87689
    Prev
    Next
    INDEX
    Explanations

    words related to government agencies and policies

    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
    isha
    -0.06
     stereotype
    -0.06
     ban
    -0.06
     Newsp
    -0.06
    let
    -0.06
    linger
    -0.06
    ara
    -0.06
    ot
    -0.05
    clock
    -0.05
    els
    -0.05
    POSITIVE LOGITS
    erset
    0.08
    gne
    0.07
    osph
    0.07
    orsch
    0.07
    auled
    0.07
    orida
    0.07
    ycop
    0.07
    ä¾µ
    0.07
    ledon
    0.07
    aktiv
    0.07
    Activations Density 0.002%

    No Known Activations