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. 15-LLAMASCOPE-RES-32K
    6. 2137
    Prev
    Next
    INDEX
    Explanations

    instances of the word "before"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olini
    -0.17
     zwar
    -0.17
    inal
    -0.16
    agli
    -0.14
    ossier
    -0.14
     sice
    -0.13
    INAL
    -0.13
    ÑĪе
    -0.13
    ongs
    -0.12
    object
    -0.12
    POSITIVE LOGITS
     ultimately
    0.18
    LEAR
    0.16
    yro
    0.16
     Ultimately
    0.15
    umber
    0.14
     addCriterion
    0.14
    zier
    0.14
    nul
    0.14
    decess
    0.14
     eventually
    0.14
    Activations Density 0.050%

    No Known Activations