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. 5-LLAMASCOPE-RES-32K
    6. 17437
    Prev
    Next
    INDEX
    Explanations

    terms related to explosive events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulo
    -0.17
    imos
    -0.16
    irm
    -0.16
    amm
    -0.15
    ulos
    -0.14
    ylül
    -0.14
    emon
    -0.14
    pire
    -0.14
     commission
    -0.14
     Gross
    -0.14
    POSITIVE LOGITS
    sole
    0.17
    983
    0.14
     Zhou
    0.14
    sip
    0.13
    wich
    0.13
    βολ
    0.13
    ¢
    0.13
    à¸ŀà¸Ń
    0.13
    /exp
    0.13
    _fatal
    0.13
    Activations Density 0.018%

    No Known Activations