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. 21-LLAMASCOPE-RES-32K
    6. 9868
    Prev
    Next
    INDEX
    Explanations

    references to historical geographical contexts and empires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obby
    -0.15
    ynom
    -0.15
    pb
    -0.15
     Alger
    -0.15
     suburban
    -0.15
    ulas
    -0.14
    quito
    -0.14
    asonic
    -0.13
    ula
    -0.13
    ared
    -0.13
    POSITIVE LOGITS
    ERICA
    0.20
     lands
    0.19
     Terra
    0.18
     territory
    0.17
    uria
    0.17
    oland
    0.17
    ланд
    0.16
     Arabia
    0.16
     territories
    0.16
    olland
    0.15
    Activations Density 0.216%

    No Known Activations