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. 16-LLAMASCOPE-RES-32K
    6. 21802
    Prev
    Next
    INDEX
    Explanations

    references to academic or educational topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dere
    -0.16
     Manga
    -0.16
    ycop
    -0.15
     pstmt
    -0.15
    /cms
    -0.15
    istrovstvÃŃ
    -0.15
    markt
    -0.14
    Ñĥнк
    -0.14
    iesel
    -0.14
    onces
    -0.14
    POSITIVE LOGITS
     Madness
    0.28
    (M
    0.18
    achuset
    0.17
    olog
    0.16
     Mir
    0.15
     Mondays
    0.15
    =M
    0.15
    (æ°´
    0.15
    ificent
    0.15
     MAGIC
    0.15
    Activations Density 1.966%

    No Known Activations