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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76564
    Prev
    Next
    INDEX
    Explanations

    opening curly braces and function definitions in code

    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
    addtogroup
    -0.08
    ResponseType
    -0.08
     dopl
    -0.08
    ickt
    -0.07
    acha
    -0.07
    bens
    -0.07
    rolls
    -0.07
    óst
    -0.07
    illance
    -0.07
     nors
    -0.07
    POSITIVE LOGITS
     return
    0.09
    return
    0.07
     throw
    0.07
    omat
    0.06
     solids
    0.06
     solid
    0.06
     Solid
    0.06
     char
    0.05
    vue
    0.05
    Solid
    0.05
    Activations Density 0.004%

    No Known Activations