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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 17815
    Prev
    Next
    INDEX
    Explanations

    company and industry names, particularly in pharmaceuticals and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uninitialized
    -0.16
    itra
    -0.16
    786
    -0.14
    iram
    -0.14
    ãĤ¶ãĥ¼
    -0.14
    ui
    -0.14
    addock
    -0.13
    od
    -0.13
     EIF
    -0.13
    uu
    -0.13
    POSITIVE LOGITS
     Inc
    0.74
    Inc
    0.59
     inc
    0.58
    inc
    0.53
     INC
    0.53
    _inc
    0.52
    -inc
    0.49
    .inc
    0.47
    INC
    0.44
     Incorporated
    0.43
    Activations Density 0.062%

    No Known Activations