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. 30-LLAMASCOPE-RES-32K
    6. 4664
    Prev
    Next
    INDEX
    Explanations

    historical or cultural references related to Indian religious figures and sites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    canf
    -0.17
     Lanc
    -0.16
     Aid
    -0.16
     syn
    -0.16
     Term
    -0.15
     impro
    -0.14
    yx
    -0.14
     Cain
    -0.14
    entes
    -0.14
     Lou
    -0.14
    POSITIVE LOGITS
    lesh
    0.28
    esh
    0.26
    appa
    0.23
    oday
    0.23
    arsing
    0.22
    argar
    0.22
    udev
    0.21
    igar
    0.20
    resh
    0.20
    war
    0.20
    Activations Density 0.290%

    No Known Activations