© 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. 25-LLAMASCOPE-RES-32K
    11. 14785
    Prev
    Next
    INDEX
    Explanations

    references to cattle and livestock-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĮ¥
    -0.16
     polar
    -0.15
    rvine
    -0.15
    γÎŃν
    -0.15
    bero
    -0.14
    æı®
    -0.14
     sach
    -0.14
    icals
    -0.14
    rat
    -0.14
    ãĥ¼ãĥł
    -0.14
    POSITIVE LOGITS
    /go
    0.20
     pens
    0.20
     raised
    0.19
    /she
    0.19
     raising
    0.19
     egret
    0.19
     rust
    0.18
     husband
    0.18
     ranch
    0.18
    her
    0.18
    Activations Density 0.025%

    No Known Activations