© 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. 12-LLAMASCOPE-RES-32K
    11. 14974
    Prev
    Next
    INDEX
    Explanations

    present participles and verb forms related to sitting or being positioned somewhere

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gov
    -0.18
    WD
    -0.17
    inos
    -0.15
    _simps
    -0.15
    night
    -0.15
    chest
    -0.15
    acht
    -0.14
    orners
    -0.14
    agon
    -0.14
    ometown
    -0.14
    POSITIVE LOGITS
    odia
    0.17
    _UNDEF
    0.15
    æ¨Ļ
    0.14
    lle
    0.14
    ãĥ³ãĥĩ
    0.14
    lassen
    0.14
    uate
    0.14
    andard
    0.13
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.13
    eken
    0.13
    Activations Density 0.079%

    No Known Activations