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. 8-LLAMASCOPE-RES-32K
    6. 6550
    Prev
    Next
    INDEX
    Explanations

    entries in a log or diary format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osemite
    -0.16
    446
    -0.14
    озв
    -0.14
    wers
    -0.14
    ashboard
    -0.14
    ·
    -0.14
    .SP
    -0.13
    ersist
    -0.13
    nez
    -0.13
     blas
    -0.13
    POSITIVE LOGITS
    िह
    0.15
    íĥķ
    0.15
    è¦
    0.15
    ä¿
    0.15
    empt
    0.14
    ildenafil
    0.14
    optera
    0.14
    .DropTable
    0.14
     consect
    0.14
    ³
    0.14
    Activations Density 0.026%

    No Known Activations