© 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. 12-LLAMASCOPE-RES-32K
    11. 14264
    Prev
    Next
    INDEX
    Explanations

    phrases related to public health and industrial safety issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jvu
    -0.18
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.18
    kowski
    -0.15
    otechn
    -0.15
     имÑĥ
    -0.15
    ocache
    -0.15
    illez
    -0.14
    arra
    -0.14
     ÑģпÑĢав
    -0.14
    ENDOR
    -0.14
    POSITIVE LOGITS
     кÑĢа
    0.14
    AGON
    0.13
    283
    0.13
    _PI
    0.13
    leg
    0.13
    ps
    0.13
    ernaut
    0.13
    ously
    0.13
    .addHandler
    0.13
    ark
    0.12
    Activations Density 0.006%

    No Known Activations