© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the word "Plus" indicating additional benefits or features

    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
    nt
    -0.22
    zelf
    -0.20
    /is
    -0.19
    chod
    -0.16
    åħ¶
    -0.15
    /place
    -0.15
    castle
    -0.15
    tube
    -0.14
    .UnitTesting
    -0.14
    å¯Ł
    -0.14
    POSITIVE LOGITS
    ieurs
    0.35
    -minus
    0.32
    minus
    0.29
     ça
    0.28
    ++++++++++++++++++++++++++++++++
    0.23
    quam
    0.22
    Minus
    0.22
    ++++++++++++++++
    0.22
    ++++
    0.21
    ++++++++
    0.20
    Activations Density 0.021%

    No Known Activations