© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 13-LLAMASCOPE-RES-32K
    6. 148
    Prev
    Next
    INDEX
    Explanations

    discussions around social contracts and personal responsibility in community contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹İ
    -0.15
    uckle
    -0.14
    orum
    -0.14
    onica
    -0.14
     Cyr
    -0.13
    ktop
    -0.13
     Jou
    -0.13
     Integr
    -0.13
    atta
    -0.13
    anych
    -0.13
    POSITIVE LOGITS
     but
    0.29
     nhưng
    0.25
    but
    0.24
     pero
    0.21
    ï¼Įä½Ĩ
    0.20
     но
    0.19
     maar
    0.19
     BUT
    0.19
     But
    0.19
    _but
    0.18
    Activations Density 0.165%

    No Known Activations