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. 17-LLAMASCOPE-RES-32K
    6. 15926
    Prev
    Next
    INDEX
    Explanations

    terms related to corporate influence on public health and safety issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åłĤ
    -0.18
    veau
    -0.18
    oble
    -0.16
    ninger
    -0.15
     Hunger
    -0.15
     tuần
    -0.15
     SCRIPT
    -0.14
    bote
    -0.14
    tridge
    -0.14
     trap
    -0.14
    POSITIVE LOGITS
     exposure
    0.30
     exposures
    0.28
     Exposure
    0.27
     exposed
    0.23
     expos
    0.23
     health
    0.22
     carcin
    0.21
     cancer
    0.21
    Exposed
    0.20
     cancers
    0.19
    Activations Density 0.249%

    No Known Activations