© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 13-LLAMASCOPE-RES-32K
    11. 26220
    Prev
    Next
    INDEX
    Explanations

    comment indicators in code

    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
    insky
    -0.17
     Downing
    -0.17
     def
    -0.15
    aves
    -0.15
    ant
    -0.15
    ique
    -0.15
    ly
    -0.15
    and
    -0.15
    ains
    -0.15
    üy
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.16
     sao
    0.16
     Dữ
    0.16
    ÑĢава
    0.16
    buat
    0.16
    çĭĤ
    0.16
    ibble
    0.16
    _charset
    0.15
    à¹Ģà¸ļ
    0.15
    .cx
    0.15
    Activations Density 0.063%

    No Known Activations