© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 14886
    Prev
    Next
    INDEX
    Explanations

    CSS properties and layout-related attributes in a stylesheet

    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
    agas
    -0.15
     Youth
    -0.15
    arian
    -0.14
    indexOf
    -0.14
    нак
    -0.14
    profits
    -0.13
    agon
    -0.13
    irates
    -0.13
     اÙĦÙħغ
    -0.13
     Mystery
    -0.13
    POSITIVE LOGITS
    sic
    0.16
    AMD
    0.14
    327
    0.14
    aison
    0.14
    ECTOR
    0.14
    _thumb
    0.14
    lu
    0.14
    526
    0.14
     titre
    0.14
    á»ı
    0.14
    Activations Density 0.029%

    No Known Activations