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. 18-LLAMASCOPE-RES-32K
    6. 24598
    Prev
    Next
    INDEX
    Explanations

    references to the term "Baker" and related variations, particularly in the context of culinary activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chez
    -0.16
    icates
    -0.16
    .scalablytyped
    -0.16
    gle
    -0.15
    rew
    -0.15
    rvine
    -0.15
    bubble
    -0.15
    erate
    -0.15
    ennent
    -0.15
    readcr
    -0.14
    POSITIVE LOGITS
     soda
    0.18
    opp
    0.15
    ove
    0.15
    emm
    0.15
    em
    0.15
     Vog
    0.15
    st
    0.15
     Weg
    0.15
     Soda
    0.15
    ronym
    0.14
    Activations Density 0.014%

    No Known Activations