© 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. 31-LLAMASCOPE-RES-32K
    11. 1606
    Prev
    Next
    INDEX
    Explanations

    references to medical or therapeutic information

    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
     --
    -0.21
     —
    -0.20
     ÂŃ
    -0.17
     hâlâ
    -0.16
     âĶĢ
    -0.16
    -plus
    -0.16
     policym
    -0.16
     --↵
    -0.15
    âĢī
    -0.15
     âĢķ
    -0.15
    POSITIVE LOGITS
     alot
    0.40
     atleast
    0.32
     whats
    0.31
     tod
    0.31
     upto
    0.25
     aprox
    0.25
     seper
    0.23
     seperate
    0.23
     thru
    0.23
     childs
    0.23
    Activations Density 2.021%

    No Known Activations