© 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. 30-LLAMASCOPE-RES-32K
    11. 4902
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and keywords related to coding errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bone
    -0.16
     Pond
    -0.15
    loon
    -0.15
    ibile
    -0.14
    ocity
    -0.14
    URLConnection
    -0.14
     Zig
    -0.14
    Bone
    -0.14
    ullo
    -0.14
    æ¨
    -0.13
    POSITIVE LOGITS
     Slug
    0.17
    lemn
    0.15
    aÅŁÄ±
    0.15
    uga
    0.14
     Lista
    0.14
    uai
    0.14
    imd
    0.14
    kie
    0.14
    afia
    0.14
    icas
    0.13
    Activations Density 0.027%

    No Known Activations