© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    derogatory terms and references to poor judgment or mistakes

    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
    交æµģ
    -0.15
    phans
    -0.14
     çģ
    -0.14
    лан
    -0.14
     desar
    -0.14
    508
    -0.14
    еÑĢин
    -0.14
    _MAJOR
    -0.14
    hz
    -0.14
    ienza
    -0.14
    POSITIVE LOGITS
    OX
    0.15
    mach
    0.13
    ìĭ±
    0.13
    iÄįe
    0.13
    elist
    0.13
    expo
    0.13
    ترÛĮÙĨ
    0.13
    thes
    0.13
     Machines
    0.13
    kinson
    0.13
    Activations Density 0.019%

    No Known Activations