© 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. 20-LLAMASCOPE-RES-32K
    11. 20260
    Prev
    Next
    INDEX
    Explanations

    references to the keyword 'self' indicating self-related method or function calls within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oneself
    -0.21
     himself
    -0.20
     themselves
    -0.20
    èĩªå·±
    -0.19
    ous
    -0.18
     ourselves
    -0.18
     myself
    -0.18
     herself
    -0.18
     yourself
    -0.17
     zich
    -0.17
    POSITIVE LOGITS
    änd
    0.26
    esteem
    0.20
    hood
    0.19
    ishly
    0.19
    ständ
    0.18
    same
    0.17
    eren
    0.17
    -contained
    0.16
    ie
    0.16
    بس
    0.15
    Activations Density 0.028%

    No Known Activations