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. 28-LLAMASCOPE-RES-32K
    6. 21012
    Prev
    Next
    INDEX
    Explanations

    occurrences of phone number formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pector
    -0.17
    Morning
    -0.16
    unsch
    -0.16
    anch
    -0.15
    995
    -0.15
    WithDuration
    -0.15
    uzzi
    -0.15
    .promise
    -0.14
    sg
    -0.14
    Ħĸ
    -0.14
    POSITIVE LOGITS
    inite
    0.16
    mts
    0.16
    rep
    0.15
    bish
    0.14
     beans
    0.14
     Hoffman
    0.14
     Run
    0.14
    /us
    0.14
    ibar
    0.14
    taire
    0.13
    Activations Density 0.012%

    No Known Activations