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. 12-LLAMASCOPE-RES-32K
    6. 13830
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to specific events or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    200
    -0.24
    Û²Û°Û°
    -0.20
     iPod
    -0.18
    Bush
    -0.17
    ovid
    -0.17
     DVDs
    -0.17
     Zoom
    -0.17
    .sourceforge
    -0.16
     Tik
    -0.16
     Bush
    -0.16
    POSITIVE LOGITS
    201
    0.27
     Zika
    0.23
     Trump
    0.22
     GDPR
    0.21
     Brexit
    0.20
     tslint
    0.20
     systemd
    0.20
     selfie
    0.19
     millennials
    0.19
    Û²Û°Û±
    0.19
    Activations Density 1.064%

    No Known Activations