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. 10-LLAMASCOPE-RES-32K
    6. 23507
    Prev
    Next
    INDEX
    Explanations

    references to published articles and their permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scratch
    -0.16
     scratching
    -0.15
    inue
    -0.14
     sur
    -0.14
    etr
    -0.14
    bart
    -0.14
    upert
    -0.14
     Lord
    -0.14
    mere
    -0.13
    tr
    -0.13
    POSITIVE LOGITS
    ávka
    0.16
    ãĥ³ãĥĹ
    0.15
    angstrom
    0.14
    OUSE
    0.14
    onda
    0.14
    vem
    0.14
    modifiable
    0.14
    ndo
    0.14
    drv
    0.14
    ียวà¸ģ
    0.14
    Activations Density 0.179%

    No Known Activations