© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 27124
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to roofing and construction services

    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
    NSE
    -0.14
     dereg
    -0.14
     Macro
    -0.14
    åºŁ
    -0.14
    iT
    -0.14
    éĥİ
    -0.14
    Macro
    -0.14
     Stein
    -0.14
    ocab
    -0.14
    rama
    -0.13
    POSITIVE LOGITS
     roof
    0.36
     roofing
    0.33
     Roof
    0.33
     roofs
    0.32
    roof
    0.28
     rooftop
    0.23
     rooft
    0.22
     pitched
    0.22
    Ro
    0.21
     attic
    0.20
    Activations Density 0.092%

    No Known Activations