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. 30-LLAMASCOPE-RES-32K
    6. 23443
    Prev
    Next
    INDEX
    Explanations

    information related to deaths and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pregnancies
    -0.14
     rencont
    -0.14
    Outlet
    -0.14
    å¬
    -0.14
    à¸ĸม
    -0.13
    ngle
    -0.13
    eload
    -0.13
    imeo
    -0.13
    pora
    -0.13
     çĬ
    -0.13
    POSITIVE LOGITS
     doctors
    0.20
     hospital
    0.20
     recuper
    0.19
     health
    0.19
     undisclosed
    0.18
     contracting
    0.18
     recovery
    0.18
    atri
    0.18
     admitted
    0.18
    -collapse
    0.17
    Activations Density 0.027%

    No Known Activations