© 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. 2-LLAMASCOPE-RES-32K
    11. 4662
    Prev
    Next
    INDEX
    Explanations

    key names and terms associated with film and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sinks
    -0.15
    accumulator
    -0.15
    cov
    -0.15
    502
    -0.15
    716
    -0.14
     лак
    -0.14
    ç§
    -0.14
     Gle
    -0.14
     Obr
    -0.14
    803
    -0.13
    POSITIVE LOGITS
    wig
    0.15
    wire
    0.15
    kc
    0.15
    anging
    0.14
     aut
    0.14
    ols
    0.14
    ept
    0.14
     Nack
    0.14
    .ColumnHeader
    0.14
    .cgi
    0.14
    Activations Density 0.357%

    No Known Activations