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. 25488
    Prev
    Next
    INDEX
    Explanations

    concepts and terminology related to health, finance, and data analysis

    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
     Jungle
    -0.15
     exit
    -0.15
     Hook
    -0.15
    odi
    -0.15
    ungle
    -0.14
    .mdl
    -0.14
    >{!!
    -0.14
    upe
    -0.14
     REC
    -0.14
    idth
    -0.14
    POSITIVE LOGITS
    alim
    0.17
    zas
    0.17
    intage
    0.17
    razier
    0.16
    ZX
    0.16
    éļª
    0.16
    ÙĦÙħÙĩ
    0.14
    äl
    0.13
    اÙĬÙĦ
    0.13
    _squared
    0.13
    Activations Density 0.051%

    No Known Activations