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. 26-LLAMASCOPE-RES-32K
    6. 1613
    Prev
    Next
    INDEX
    Explanations

    themes related to social and cultural identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loff
    -0.15
    Visibility
    -0.15
     Bram
    -0.14
    ansk
    -0.14
    getter
    -0.14
     Carlson
    -0.14
    tep
    -0.13
    Ù쨳
    -0.13
     
    -0.13
    ullen
    -0.13
    POSITIVE LOGITS
     nature
    0.43
     aspect
    0.39
     element
    0.37
    nature
    0.35
     aspects
    0.33
     angle
    0.32
     component
    0.31
     flavor
    0.31
    aspect
    0.31
     bent
    0.30
    Activations Density 0.265%

    No Known Activations