© 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. 24-LLAMASCOPE-RES-32K
    11. 9978
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to citizenship and immigration rights

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Citizens
    -0.23
     citizens
    -0.23
     citizen
    -0.21
     CIT
    -0.20
    Cit
    -0.18
     Citizen
    -0.18
    cit
    -0.17
     Citadel
    -0.16
     cit
    -0.16
     citt
    -0.16
    POSITIVE LOGITS
     Acquisition
    0.24
     acquisition
    0.23
     natural
    0.21
     acquired
    0.21
     ren
    0.20
     Natural
    0.19
     acquire
    0.19
     наÑĤÑĥ
    0.18
     acquisitions
    0.17
     acquiring
    0.17
    Activations Density 0.005%

    No Known Activations