Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96165
    Prev
    Next
    INDEX
    Explanations

    programming and code-related elements

    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
    alem
    -0.07
    pdo
    -0.07
    ί
    -0.06
    onna
    -0.06
    avn
    -0.06
    rylic
    -0.06
    lse
    -0.06
    enuity
    -0.06
    urally
    -0.06
    oyo
    -0.06
    POSITIVE LOGITS
    ONTAL
    0.07
    èn
    0.06
    exels
    0.06
    âĸ²
    0.06
    shit
    0.06
    íķ©
    0.06
     ActionTypes
    0.06
    atto
    0.06
    PB
    0.06
    MouseButton
    0.06
    Activations Density 0.013%

    No Known Activations