Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-LLAMASCOPE-RES-32K
    6. 18398
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific advancements and research in embryology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustos
    -0.15
    strup
    -0.15
    cerer
    -0.15
    izoph
    -0.15
    Ïģά
    -0.15
    ÏĦÎŃÏģα
    -0.14
    ç¸
    -0.14
    åIJĪåIJĮ
    -0.14
    ifu
    -0.14
     Pazar
    -0.14
    POSITIVE LOGITS
     prere
    0.16
    olle
    0.15
     Barbar
    0.14
    ed
    0.14
    eka
    0.13
    REA
    0.13
     GANG
    0.13
    edral
    0.13
    äºİ
    0.13
    !
    0.12
    Activations Density 0.046%

    No Known Activations