© 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. 22-LLAMASCOPE-RES-32K
    11. 3533
    Prev
    Next
    INDEX
    Explanations

    key entities, statistics, and roles within organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Engineer
    -0.17
     Officer
    -0.17
     Lawyer
    -0.16
     Brew
    -0.16
     astronaut
    -0.16
    CHASE
    -0.15
     Officers
    -0.14
     librarian
    -0.14
     Hubb
    -0.14
     pharmacist
    -0.14
    POSITIVE LOGITS
     providers
    0.23
     creators
    0.23
     implement
    0.23
     provider
    0.22
     makers
    0.21
     users
    0.21
    users
    0.20
     propos
    0.20
     maker
    0.20
    mitters
    0.20
    Activations Density 0.577%

    No Known Activations