© 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. 16-LLAMASCOPE-RES-32K
    11. 21599
    Prev
    Next
    INDEX
    Explanations

    terms related to chronic conditions and their documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .UnitTesting
    -0.18
    fdc
    -0.15
    erville
    -0.15
    sonian
    -0.15
    agers
    -0.15
    .VisualBasic
    -0.14
    æģ¯
    -0.14
    TimeStamp
    -0.14
     Muss
    -0.13
    adol
    -0.13
    POSITIVE LOGITS
    istically
    0.17
    ystal
    0.17
    enef
    0.15
    .experimental
    0.15
    keeper
    0.15
    RACT
    0.14
    Smarty
    0.14
    hardt
    0.14
    ijn
    0.14
    yms
    0.14
    Activations Density 0.020%

    No Known Activations