© 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. 20-LLAMASCOPE-RES-32K
    11. 11700
    Prev
    Next
    INDEX
    Explanations

    economic indicators related to supply and demand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _SE
    -0.15
    sv
    -0.15
     Field
    -0.14
     Wong
    -0.14
     repro
    -0.13
    astle
    -0.13
     Friedman
    -0.13
     Skip
    -0.13
    ofil
    -0.13
    /_
    -0.13
    POSITIVE LOGITS
     demand
    0.24
     Demand
    0.23
    demand
    0.20
    éľĢæ±Ĥ
    0.19
    Demand
    0.18
    -demand
    0.16
     demande
    0.16
    ãģĭãĤı
    0.16
    _demand
    0.16
     ÑģпÑĢоÑģ
    0.15
    Activations Density 0.039%

    No Known Activations