© 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. 17-LLAMASCOPE-RES-32K
    11. 5607
    Prev
    Next
    INDEX
    Explanations

    industry-specific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oker
    -0.15
    883
    -0.15
    /Branch
    -0.15
    aday
    -0.15
     Plasma
    -0.14
    actal
    -0.14
    istrovstvÃŃ
    -0.14
    bane
    -0.14
    days
    -0.14
    itchen
    -0.14
    POSITIVE LOGITS
     industry
    0.28
     sector
    0.22
     Industry
    0.21
    -grade
    0.19
    industry
    0.19
    Industry
    0.17
     à¤ľà¤Ĺ
    0.16
    è¡Įä¸ļ
    0.16
     grade
    0.16
     industries
    0.16
    Activations Density 0.318%

    No Known Activations