© 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. 22-LLAMASCOPE-RES-131K
    6. 4331
    Prev
    Next
    INDEX
    Explanations

    elements related to astronomical 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
    Uvs
    -0.08
    UpDown
    -0.08
     prostituer
    -0.08
    dda
    -0.08
    KHR
    -0.08
     Ulus
    -0.07
     erotiske
    -0.07
    >manual
    -0.07
    _Osc
    -0.07
     frække
    -0.07
    POSITIVE LOGITS
     shadow
    0.07
    .shadow
    0.06
     Official
    0.06
    ..
    0.06
    shadow
    0.05
     ê³µìĭĿ
    0.05
     officially
    0.05
     Receiver
    0.05
     dark
    0.05
     Shadow
    0.05
    Activations Density 0.001%

    No Known Activations