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. 24-LLAMASCOPE-RES-32K
    6. 5856
    Prev
    Next
    INDEX
    Explanations

    references to health, wellness, and dietary topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignon
    -0.13
     Continue
    -0.12
    ,and
    -0.12
    ,but
    -0.12
    ,â̦↵↵
    -0.12
    вала
    -0.12
     ngang
    -0.12
    ô
    -0.11
    ,it
    -0.11
     آباد
    -0.11
    POSITIVE LOGITS
    %C
    0.18
    &#
    0.17
     %↵↵
    0.13
    $LANG
    0.13
     облиÑĩ
    0.13
     \'
    0.13
     /↵↵
    0.12
     uintptr
    0.12
    Ãķ
    0.12
    URLException
    0.12
    Activations Density 0.872%

    No Known Activations