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. 23-LLAMASCOPE-RES-32K
    6. 760
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing validation or emphasis on points made in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     både
    -0.16
    xies
    -0.15
    antine
    -0.15
    ãĥªãĤ¢
    -0.15
    ansk
    -0.14
    ago
    -0.14
    ront
    -0.14
    çĶļèĩ³
    -0.14
    xbc
    -0.14
    ả
    -0.14
    POSITIVE LOGITS
     though
    0.28
     when
    0.21
    Though
    0.21
     those
    0.20
    when
    0.19
    though
    0.19
     if
    0.19
    -handed
    0.19
     within
    0.18
     worse
    0.18
    Activations Density 0.029%

    No Known Activations