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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-LLAMASCOPE-RES-32K
    6. 15100
    Prev
    Next
    INDEX
    Explanations

    historical references to significant individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gaut
    -0.16
     roma
    -0.14
     Jordan
    -0.14
     Hamas
    -0.14
     Bou
    -0.14
     neighbors
    -0.14
     Cabr
    -0.14
     youth
    -0.13
     Mant
    -0.13
     Republic
    -0.13
    POSITIVE LOGITS
     British
    0.26
    British
    0.26
     colonial
    0.23
     british
    0.22
     Colonial
    0.21
    189
    0.20
     Europeans
    0.20
    188
    0.19
    èĭ±åĽ½
    0.19
    190
    0.19
    Activations Density 0.378%

    No Known Activations