© 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. 28-LLAMASCOPE-RES-32K
    11. 17474
    Prev
    Next
    INDEX
    Explanations

    terms related to confidentiality and the protection of sensitive information

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸ģ
    -0.14
    озв
    -0.14
    kt
    -0.13
    929
    -0.13
    .xz
    -0.13
    927
    -0.12
     neglected
    -0.12
     rall
    -0.12
    267
    -0.12
    á»ħ
    -0.12
    POSITIVE LOGITS
     secret
    0.56
     secrets
    0.56
     confidential
    0.52
     secrecy
    0.52
     confidentiality
    0.46
     Confidential
    0.44
    secret
    0.44
    ç§ĺ
    0.44
     Secrets
    0.43
     Secret
    0.42
    Activations Density 0.291%

    No Known Activations