© 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. 4-LLAMASCOPE-RES-32K
    11. 23378
    Prev
    Next
    INDEX
    Explanations

    phrases related to "shutting down" or "closure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.18
     Gors
    -0.15
    INGLE
    -0.15
    ingle
    -0.15
    862
    -0.14
     herr
    -0.14
    heiten
    -0.14
    aar
    -0.14
    ql
    -0.14
    entric
    -0.14
    POSITIVE LOGITS
    -up
    0.16
    ters
    0.16
    átek
    0.15
    iram
    0.15
    abble
    0.15
    опаÑģ
    0.15
    -off
    0.14
    ozor
    0.14
    tdown
    0.14
    ë¡
    0.14
    Activations Density 0.010%

    No Known Activations