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. 20-LLAMASCOPE-RES-32K
    6. 23749
    Prev
    Next
    INDEX
    Explanations

    references to various global contexts and how they affect society and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okol
    -0.17
    outil
    -0.15
    å¹¹
    -0.14
    IED
    -0.14
    ainting
    -0.14
    ongyang
    -0.14
    eÅŁ
    -0.13
     ********************************************************
    -0.13
     CascadeType
    -0.13
    rowsable
    -0.13
    POSITIVE LOGITS
     whose
    0.27
     full
    0.20
     where
    0.18
     otherwise
    0.18
    whose
    0.18
    -wide
    0.18
     intent
    0.17
    intent
    0.16
     already
    0.15
     prem
    0.14
    Activations Density 0.133%

    No Known Activations