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. 8-LLAMASCOPE-RES-32K
    6. 7809
    Prev
    Next
    INDEX
    Explanations

    text that indicates or describes authorship or ownership in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aldi
    -0.17
    kou
    -0.15
    eyh
    -0.15
    ardi
    -0.15
    basket
    -0.15
    lesia
    -0.15
    gment
    -0.14
     Principal
    -0.14
    licant
    -0.14
    abis
    -0.14
    POSITIVE LOGITS
    rez
    0.18
    éł¼
    0.17
     Hunter
    0.15
    nave
    0.15
    things
    0.15
    fusion
    0.14
    ches
    0.14
     import
    0.14
    zes
    0.14
     Ballard
    0.13
    Activations Density 0.011%

    No Known Activations