© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to evidence and court procedures

    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
    alars
    -0.14
    arus
    -0.14
    åĨĬ
    -0.14
    ago
    -0.14
    raj
    -0.14
    UDO
    -0.14
    udev
    -0.14
     Aviv
    -0.13
    é¢Ŀ
    -0.13
     cazzo
    -0.13
    POSITIVE LOGITS
    ÑĢиÑĩ
    0.14
     Hutch
    0.13
     Belle
    0.13
     paran
    0.13
     rond
    0.13
     junge
    0.13
    OPLE
    0.13
    mention
    0.13
    erken
    0.13
     distr
    0.12
    Activations Density 0.135%

    No Known Activations