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. 6-LLAMASCOPE-RES-32K
    6. 7888
    Prev
    Next
    INDEX
    Explanations

    technical language related to data structures and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igin
    -0.19
     Latter
    -0.17
    AMED
    -0.17
    ubber
    -0.16
    ýt
    -0.16
    vro
    -0.16
    etter
    -0.15
    asin
    -0.15
    ornment
    -0.15
     boca
    -0.15
    POSITIVE LOGITS
     global
    0.16
    etag
    0.15
    IMS
    0.15
     Fay
    0.14
    WHITE
    0.14
    oire
    0.14
    iller
    0.14
     myself
    0.14
     how
    0.14
     at
    0.13
    Activations Density 0.181%

    No Known Activations