Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 1113
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts, especially related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nga
    -0.17
    å¤ķ
    -0.17
    otten
    -0.16
    zung
    -0.16
    asca
    -0.16
    otto
    -0.16
    isse
    -0.16
    sov
    -0.15
     lÃłng
    -0.15
    liner
    -0.15
    POSITIVE LOGITS
    unik
    0.16
    cle
    0.15
     sil
    0.15
     Technician
    0.15
    fdc
    0.15
     folk
    0.14
     Cure
    0.14
     Gaz
    0.14
     F
    0.14
     Word
    0.14
    Activations Density 0.005%

    No Known Activations