© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 16928
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical expressions and scientific notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allowable
    -0.18
    anz
    -0.14
     verst
    -0.14
    cheid
    -0.14
    edb
    -0.13
    Snap
    -0.13
    %;"
    -0.13
    æ£ĭçīĮ
    -0.13
    verity
    -0.13
     Powers
    -0.13
    POSITIVE LOGITS
    cobra
    0.16
    _nr
    0.15
     íά
    0.15
    addtogroup
    0.14
     UL
    0.14
    ullan
    0.14
    rellas
    0.14
    hammer
    0.14
     hammer
    0.14
    anean
    0.14
    Activations Density 2.126%

    No Known Activations