© 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. 26-LLAMASCOPE-RES-32K
    11. 1273
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emma
    -0.16
    -mf
    -0.16
    adla
    -0.15
    TransparentColor
    -0.15
    heimer
    -0.15
    ButtonTitles
    -0.15
    undler
    -0.15
     RouteServiceProvider
    -0.15
    starter
    -0.14
    dale
    -0.14
    POSITIVE LOGITS
    richt
    0.23
     controls
    0.23
     accord
    0.22
     richt
    0.20
     components
    0.20
     radi
    0.18
     Controls
    0.18
     Richt
    0.18
    controls
    0.18
     component
    0.18
    Activations Density 0.251%

    No Known Activations