© 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. 28-LLAMASCOPE-RES-32K
    11. 128
    Prev
    Next
    INDEX
    Explanations

    references to regulations, programs, and potential issues related to public safety and privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å»Ĭ
    -0.16
     DM
    -0.15
     Col
    -0.15
    .pm
    -0.15
    cloud
    -0.15
     Saunders
    -0.15
     col
    -0.14
    .kr
    -0.14
    Col
    -0.14
    Cloud
    -0.14
    POSITIVE LOGITS
     cas
    0.18
    rams
    0.18
    oram
    0.18
    urga
    0.17
    CAS
    0.16
     Lama
    0.16
     CAS
    0.16
    лам
    0.15
     Cass
    0.15
     RAM
    0.15
    Activations Density 0.026%

    No Known Activations