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. 29-LLAMASCOPE-RES-32K
    6. 12358
    Prev
    Next
    INDEX
    Explanations

    complex relationships and calculations involving mathematical or scientific principles, especially around light, structure, and financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Credential
    -0.20
    CONTEXT
    -0.16
     Canter
    -0.16
    icolon
    -0.16
     Cust
    -0.16
    (Canvas
    -0.16
     Cout
    -0.16
    Ðĭ
    -0.15
     Crypt
    -0.15
     Cuisine
    -0.15
    POSITIVE LOGITS
     c
    1.48
    c
    0.93
    .c
    0.81
    Âłc
    0.72
    (c
    0.72
    )c
    0.70
    "c
    0.67
    	c
    0.66
    =c
    0.64
    *c
    0.64
    Activations Density 0.204%

    No Known Activations