© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24040
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to defining and manipulating variables, aliases, and data structures in code

    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
    )↵↵↵↵
    -0.16
    ")↵↵↵
    -0.16
    ()"↵
    -0.16
    )↵↵↵
    -0.15
    ())↵↵↵
    -0.15
    )↵↵↵↵↵
    -0.15
    (ByVal
    -0.15
     )↵↵↵
    -0.15
    )↵↵↵↵↵↵
    -0.15
    "↵↵↵
    -0.15
    POSITIVE LOGITS
    ;↵
    0.88
    ;↵↵
    0.77
     ;↵
    0.66
    ();↵
    0.66
    ï¼Ľ↵
    0.65
    _;↵
    0.63
    .;↵
    0.63
    ?;↵
    0.60
    ';↵
    0.60
    ";↵
    0.58
    Activations Density 0.710%

    No Known Activations