© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 20695
    Prev
    Next
    INDEX
    Explanations

    elements related to programming, specifically variable handling and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nun
    -0.22
     nu
    -0.22
     nos
    -0.21
     nip
    -0.20
    /n
    -0.20
    @n
    -0.19
    =n
    -0.19
     nudity
    -0.19
     nou
    -0.19
    (n
    -0.18
    POSITIVE LOGITS
    Name
    0.73
     Name
    0.62
    _Name
    0.52
    _name
    0.52
    _NAME
    0.51
    	Name
    0.48
    NAME
    0.45
    .Name
    0.44
    Nam
    0.43
    -name
    0.42
    Activations Density 0.033%

    No Known Activations