© 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. 23-LLAMASCOPE-RES-32K
    11. 1650
    Prev
    Next
    INDEX
    Explanations

    questions or phrases related to inquiry and seeking detailed information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewn
    -0.17
    itia
    -0.15
    idis
    -0.15
    adier
    -0.15
     physic
    -0.14
    emma
    -0.14
    imity
    -0.14
    stown
    -0.14
    .gdx
    -0.13
    isas
    -0.13
    POSITIVE LOGITS
     much
    0.37
    much
    0.29
     many
    0.29
     Much
    0.28
    Much
    0.26
     MUCH
    0.25
    many
    0.23
     mucho
    0.22
     muchos
    0.21
     often
    0.19
    Activations Density 0.051%

    No Known Activations