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. 2-LLAMASCOPE-RES-32K
    6. 101
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the exclusion or possibility of options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lamaz
    -0.17
    atur
    -0.16
    Ä
    -0.16
     Montgomery
    -0.15
    NAL
    -0.14
    βα
    -0.14
    529
    -0.14
    ULA
    -0.14
    blo
    -0.14
    ertz
    -0.14
    POSITIVE LOGITS
     Sanayi
    0.18
    redits
    0.15
    alaria
    0.15
    >({
    0.14
    tery
    0.14
    iated
    0.14
    .builder
    0.14
    gee
    0.14
     possibilit
    0.13
    ç»Ŀ
    0.13
    Activations Density 0.011%

    No Known Activations