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. 8-LLAMASCOPE-RES-32K
    6. 6522
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparation and readiness for events or activities

    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
    asad
    -0.16
    umont
    -0.16
    roids
    -0.14
    ivet
    -0.14
    anka
    -0.14
    earer
    -0.14
    ÃŃky
    -0.14
    cached
    -0.14
    postData
    -0.14
     дов
    -0.14
    POSITIVE LOGITS
    ìĿį
    0.16
    usta
    0.15
    _MIX
    0.14
    igans
    0.14
    yan
    0.14
    \Json
    0.14
    icha
    0.13
    ned
    0.13
    ade
    0.13
    ãģıãĤĭ
    0.13
    Activations Density 0.078%

    No Known Activations