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. 30-LLAMASCOPE-RES-32K
    6. 23389
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions

    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
    лив
    -0.17
     pari
    -0.16
    acket
    -0.15
    glich
    -0.14
    doch
    -0.14
    atem
    -0.14
    cz
    -0.14
    imers
    -0.14
    ikal
    -0.14
    ãĤ¤ãĤ¯
    -0.14
    POSITIVE LOGITS
    abl
    0.22
    oline
    0.21
    o
    0.20
    omencl
    0.18
    oise
    0.17
    u
    0.17
    ueva
    0.16
    idia
    0.16
    ab
    0.16
    \n
    0.16
    Activations Density 0.008%

    No Known Activations