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. 16-LLAMASCOPE-RES-32K
    6. 8444
    Prev
    Next
    INDEX
    Explanations

    various data types and specifications used in programming

    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
     shape
    -0.15
    [args
    -0.15
    ugi
    -0.15
    ston
    -0.14
    uffman
    -0.14
    onda
    -0.14
    irs
    -0.14
     Ro
    -0.13
     rap
    -0.13
     dem
    -0.13
    POSITIVE LOGITS
     ник
    0.15
    imizer
    0.14
     extingu
    0.14
    elper
    0.13
     false
    0.13
    ån
    0.13
    /moment
    0.13
    han
    0.13
     (("
    0.13
    (false
    0.13
    Activations Density 0.065%

    No Known Activations