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. 15-LLAMASCOPE-RES-32K
    6. 9467
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     being
    -0.15
    ENCY
    -0.15
    ι
    -0.14
    lightbox
    -0.14
    asyon
    -0.14
    wnd
    -0.14
    being
    -0.14
    ami
    -0.14
    amps
    -0.14
    edBy
    -0.14
    POSITIVE LOGITS
    ÅĤa
    0.18
     no
    0.17
    ome
    0.14
    apus
    0.14
    htm
    0.14
     more
    0.14
    UnitTest
    0.13
     ÙĪØ§ØŃد
    0.13
    alled
    0.13
     corresponding
    0.13
    Activations Density 0.015%

    No Known Activations