© 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. 31-LLAMASCOPE-RES-32K
    11. 18395
    Prev
    Next
    INDEX
    Explanations

    specific terms related to academic and educational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    μαν
    -0.13
    енное
    -0.13
    sworth
    -0.12
    ÑĢап
    -0.12
    esub
    -0.12
    /callback
    -0.12
    ÑĤим
    -0.12
    prech
    -0.11
    ipse
    -0.11
    æĽľ
    -0.11
    POSITIVE LOGITS
     level
    1.28
    level
    1.07
     levels
    1.03
     Level
    1.01
    -level
    0.97
     LEVEL
    0.94
    Level
    0.93
    _level
    0.91
    .level
    0.88
    levels
    0.87
    Activations Density 0.196%

    No Known Activations