© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 24134
    Prev
    Next
    INDEX
    Explanations

    terms related to construction, renovation, and repair activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     हल
    -0.17
    ëŀ
    -0.16
    anggan
    -0.15
    _CRE
    -0.15
    اÙĦÙĩ
    -0.14
    ãĥªãĤ«
    -0.14
    skirts
    -0.14
    issant
    -0.14
    olls
    -0.14
    otate
    -0.14
    POSITIVE LOGITS
     infrastructure
    0.28
     existing
    0.23
     aging
    0.20
     ageing
    0.19
     worn
    0.19
     neglected
    0.19
     entire
    0.19
     Infrastructure
    0.19
     equipment
    0.19
     structures
    0.19
    Activations Density 0.174%

    No Known Activations