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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10075
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-improvement and personal development through a faith-based lens

    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
    ãĥ«ãĥī
    -0.14
     compar
    -0.14
     representative
    -0.14
    GLOSS
    -0.14
    subtype
    -0.14
     addCriterion
    -0.13
    wiÄħ
    -0.13
    енÑĮ
    -0.13
    Æ°ng
    -0.13
    ders
    -0.13
    POSITIVE LOGITS
     proven
    0.36
     practical
    0.34
     concrete
    0.29
     Practical
    0.25
     Concrete
    0.25
    Concrete
    0.24
     proved
    0.24
     step
    0.24
    -tested
    0.23
     tools
    0.23
    Activations Density 0.144%

    No Known Activations