© 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. 29-LLAMASCOPE-RES-32K
    11. 4216
    Prev
    Next
    INDEX
    Explanations

    references to structures, frameworks, or formats within organized data or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGIN
    -0.12
    lias
    -0.12
    kich
    -0.11
    uitka
    -0.11
     InitializeComponent
    -0.11
    견
    -0.11
    ////////////////////////////////////////////////////////////////////////////////↵↵
    -0.11
    éłĥ
    -0.11
    -нибÑĥдÑĮ
    -0.11
    /Application
    -0.11
    POSITIVE LOGITS
     only
    1.54
    only
    1.34
     Only
    1.27
     ONLY
    1.27
    Only
    1.21
    _only
    1.12
    ONLY
    1.08
    -only
    1.04
    _ONLY
    0.98
    .only
    0.96
    Activations Density 2.039%

    No Known Activations