© 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. 10-LLAMASCOPE-RES-32K
    11. 9638
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant achievements or milestones in education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ïİ
    -0.16
     Edgar
    -0.15
    atorial
    -0.15
    scar
    -0.15
    ÑĨÑĥз
    -0.15
    aland
    -0.14
    çĮĽ
    -0.14
    idas
    -0.14
     jack
    -0.14
    _hpp
    -0.14
    POSITIVE LOGITS
    ezi
    0.15
     Bend
    0.15
    ieder
    0.14
    inic
    0.14
    arked
    0.14
    اÙĪت
    0.14
     _|
    0.14
    edReader
    0.14
    ording
    0.13
    ods
    0.13
    Activations Density 0.457%

    No Known Activations