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. 20-LLAMASCOPE-RES-32K
    6. 23786
    Prev
    Next
    INDEX
    Explanations

    competitive sports events and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    884
    -0.16
    jab
    -0.15
     ing
    -0.15
    çª
    -0.15
    ÄĻ
    -0.14
    .rs
    -0.14
    æı´
    -0.14
    ersiz
    -0.14
     Reggie
    -0.14
     cage
    -0.14
    POSITIVE LOGITS
     horses
    0.18
     pon
    0.18
    anken
    0.17
    horse
    0.17
    jump
    0.16
     geld
    0.16
     Equ
    0.15
     jumping
    0.15
     horse
    0.15
    Brains
    0.15
    Activations Density 0.022%

    No Known Activations