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. 15-LLAMASCOPE-RES-32K
    6. 2268
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to legal injunctions and restrictions

    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
     mastur
    -0.13
     quo
    -0.13
    â̦but
    -0.12
    ,
    -0.12
     PROCUREMENT
    -0.12
    -cycle
    -0.12
     til
    -0.12
    â̦
    -0.12
    ноÑģÑĤ
    -0.12
    ãĤ¢ãĥ¼
    -0.12
    POSITIVE LOGITS
    rish
    0.14
     )↵↵↵↵↵↵↵↵
    0.14
    ounder
    0.13
    InstanceOf
    0.13
    uther
    0.12
    isman
    0.12
    ypical
    0.12
    indr
    0.12
     ingresar
    0.12
    ishi
    0.12
    Activations Density 0.062%

    No Known Activations