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. 31-LLAMASCOPE-RES-32K
    6. 6769
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuations and structural elements in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SELL
    -0.16
     chron
    -0.15
    Seller
    -0.15
     Seller
    -0.15
    .gdx
    -0.14
    Salary
    -0.14
    Profit
    -0.14
     Publishers
    -0.14
    _Client
    -0.13
     history
    -0.13
    POSITIVE LOGITS
     Stars
    0.25
     Rays
    0.21
     Astr
    0.20
    Stars
    0.20
     Jets
    0.20
     Winds
    0.19
     Bright
    0.19
     Aster
    0.19
     Colors
    0.19
     Shadows
    0.18
    Activations Density 0.040%

    No Known Activations