© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 2752
    Prev
    Next
    INDEX
    Explanations

    references to past events or decisions with a focus on accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ť
    -0.14
    xffffff
    -0.14
    μÎŃ
    -0.12
     behalf
    -0.12
    SSION
    -0.12
    IPA
    -0.12
    erta
    -0.12
     humble
    -0.12
     ë°ĶëĿ¼
    -0.11
     accompany
    -0.11
    POSITIVE LOGITS
     somebody
    0.19
     they
    0.17
    someone
    0.17
    they
    0.17
     someone
    0.16
    orgot
    0.15
     THEY
    0.14
    irut
    0.14
    bout
    0.14
     we
    0.14
    Activations Density 1.166%

    No Known Activations