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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27531
    Prev
    Next
    INDEX
    Explanations

    references to prisons and their associated programs or issues

    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
    ุà¹Ī
    -0.15
    ëł¹
    -0.14
     صÙĦÙī
    -0.14
    aar
    -0.13
    pert
    -0.13
    _sampler
    -0.13
    ãĤĵãģ¨
    -0.13
    аÑĤи
    -0.13
    Insurance
    -0.12
    ÏģÎŃ
    -0.12
    POSITIVE LOGITS
     prison
    0.79
     Prison
    0.71
     prisoner
    0.68
     prisoners
    0.66
     inmate
    0.65
     jail
    0.64
     prisons
    0.62
     inmates
    0.61
     Jail
    0.55
     Corrections
    0.52
    Activations Density 0.303%

    No Known Activations