© 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. 21-LLAMASCOPE-RES-32K
    11. 4828
    Prev
    Next
    INDEX
    Explanations

    references to the Marvel franchise and its related media

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    esy
    -0.16
    esi
    -0.16
    ether
    -0.16
    eses
    -0.15
    equ
    -0.15
    ees
    -0.15
    ecc
    -0.14
    ople
    -0.14
    edian
    -0.14
     Jays
    -0.14
    POSITIVE LOGITS
    ously
    0.32
    ous
    0.31
    icious
    0.30
     Cin
    0.20
    ment
    0.19
    otta
    0.19
    OUS
    0.19
    lez
    0.19
    ulous
    0.19
     Comics
    0.18
    Activations Density 0.004%

    No Known Activations