© 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. 17-LLAMASCOPE-RES-32K
    11. 11641
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to abstract classes and inheritance in object-oriented programming

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    iag
    -0.15
    Æ°á»Ľi
    -0.15
    ront
    -0.14
    eldon
    -0.14
    blas
    -0.14
    urai
    -0.14
     Marty
    -0.13
     Wing
    -0.13
     circ
    -0.13
    unn
    -0.13
    POSITIVE LOGITS
    abstract
    0.31
     abstract
    0.31
    abstractmethod
    0.27
    _abstract
    0.22
     Concrete
    0.20
     NotImplementedError
    0.20
    Concrete
    0.20
    æĬ½
    0.19
    protected
    0.19
    _Abstract
    0.19
    Activations Density 0.040%

    No Known Activations