© 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 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. 16-LLAMASCOPE-RES-32K
    11. 19639
    Prev
    Next
    INDEX
    Explanations

    references to political figures and issues related to social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /debug
    -0.15
    ronic
    -0.15
    arness
    -0.15
     chung
    -0.14
    andex
    -0.14
    rna
    -0.14
    mobx
    -0.14
     mặc
    -0.13
     kitty
    -0.13
    rn
    -0.13
    POSITIVE LOGITS
     speech
    0.19
     statements
    0.18
     inflammatory
    0.18
     statement
    0.17
    ocaust
    0.16
     words
    0.16
    ulk
    0.15
     his
    0.15
     sensitivity
    0.14
     Ñģлова
    0.14
    Activations Density 0.205%

    No Known Activations