© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 17914
    Prev
    Next
    INDEX
    Explanations

    terms associated with various forms of censorship and control

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    			↵
    -0.22
    ialis
    -0.21
    OrCreate
    -0.19
    coming
    -0.18
    			↵			↵
    -0.18
    orsi
    -0.18
    sv
    -0.17
    ERSHEY
    -0.17
                ↵            ↵
    -0.17
    ologne
    -0.17
    POSITIVE LOGITS
    wealth
    0.19
    ifornia
    0.18
    pillar
    0.18
    stalk
    0.17
    punk
    0.16
    members
    0.16
    =C
    0.15
    enne
    0.15
     vast
    0.15
    agne
    0.15
    Activations Density 1.154%

    No Known Activations