© 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. 25-LLAMASCOPE-RES-32K
    11. 10472
    Prev
    Next
    INDEX
    Explanations

    interactions and inquiries related to assistance or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ypress
    -0.14
    erdings
    -0.13
    æı®
    -0.12
    å³°
    -0.12
    -CN
    -0.12
    vell
    -0.12
    FACT
    -0.12
     Feinstein
    -0.12
    fte
    -0.12
    лаÑĢа
    -0.12
    POSITIVE LOGITS
     find
    1.03
     finds
    0.96
    find
    0.91
     finding
    0.90
     found
    0.90
     Find
    0.86
    -find
    0.82
    .find
    0.82
    Find
    0.82
     FIND
    0.81
    Activations Density 0.546%

    No Known Activations