© 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. 13-LLAMASCOPE-RES-32K
    11. 16174
    Prev
    Next
    INDEX
    Explanations

    themes related to moral and ethical responsibility and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innoc
    -0.16
    atitude
    -0.15
    reative
    -0.14
    assa
    -0.14
    929
    -0.14
    154
    -0.14
     grazing
    -0.14
     Lantern
    -0.14
    inz
    -0.14
     Reporter
    -0.14
    POSITIVE LOGITS
    iens
    0.17
    å¹
    0.15
    ascimento
    0.15
    lops
    0.14
    δι
    0.14
    FIN
    0.14
    ainer
    0.14
    CurrentValue
    0.14
    tu
    0.13
     sır
    0.13
    Activations Density 0.262%

    No Known Activations