© 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. 2-LLAMASCOPE-RES-32K
    11. 9194
    Prev
    Next
    INDEX
    Explanations

    references to the rating system for media content, particularly focusing on "PG" and variations of it

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    oir
    -0.17
    elize
    -0.15
    DataContract
    -0.15
    687
    -0.15
    arios
    -0.14
    .ops
    -0.14
    ods
    -0.14
    ạo
    -0.14
    iflower
    -0.14
    961
    -0.14
    POSITIVE LOGITS
    chin
    0.16
    анÑģи
    0.15
    ignite
    0.15
    antz
    0.15
    ioned
    0.15
    Å¡ka
    0.15
    kem
    0.14
    žel
    0.14
    anske
    0.14
    arena
    0.14
    Activations Density 0.014%

    No Known Activations