Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 3414
    Prev
    Next
    INDEX
    Explanations

    terms related to patent law and the patenting process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赤
    -0.14
     Hunger
    -0.14
    zug
    -0.14
    ÌĨ
    -0.13
    (æľ¨
    -0.13
     Incontri
    -0.13
    antlr
    -0.13
    idak
    -0.13
    .initState
    -0.13
    plr
    -0.13
    POSITIVE LOGITS
     patent
    0.61
     Patent
    0.54
     patents
    0.53
    pat
    0.46
    Pat
    0.45
     Pat
    0.43
     invention
    0.42
     inventions
    0.41
     паÑĤ
    0.40
     Invent
    0.40
    Activations Density 0.051%

    No Known Activations