© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 15827
    Prev
    Next
    INDEX
    Explanations

    the word "there" in various contexts, indicating discussions about presence or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comes
    -0.16
    antage
    -0.16
    brook
    -0.15
    ÑģÑĮого
    -0.15
     Sites
    -0.15
    롯
    -0.14
    moth
    -0.14
    हन
    -0.14
    ollision
    -0.14
    YW
    -0.14
    POSITIVE LOGITS
     had
    0.17
     appearing
    0.17
     appear
    0.17
     continue
    0.17
     were
    0.16
     appeared
    0.16
     appears
    0.15
     continues
    0.15
     remain
    0.15
     currently
    0.15
    Activations Density 0.063%

    No Known Activations