© 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. 14693
    Prev
    Next
    INDEX
    Explanations

    numerical data formats and values, particularly dates and identifiers

    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
    INGER
    -0.15
     عد
    -0.15
    inger
    -0.15
     bac
    -0.14
    çak
    -0.14
    ?action
    -0.14
    uche
    -0.14
    .Actions
    -0.13
     btnCancel
    -0.13
    åĨĴ
    -0.13
    POSITIVE LOGITS
    iscard
    0.21
    دÙĪد
    0.17
    iÃŁ
    0.15
     Reload
    0.14
    abox
    0.14
    psy
    0.14
    اÙģت
    0.14
    æľ
    0.14
    roj
    0.14
    ValuePair
    0.13
    Activations Density 0.002%

    No Known Activations