© 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. 14877
    Prev
    Next
    INDEX
    Explanations

    terms associated with risk reduction and safety measures

    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
    VEC
    -0.15
    slu
    -0.15
    _leaf
    -0.15
    RTL
    -0.15
    .truth
    -0.15
    azel
    -0.15
    eel
    -0.14
     çĬ
    -0.14
    aybe
    -0.14
    خاÙĨÙĩ
    -0.14
    POSITIVE LOGITS
    /mit
    0.14
    /block
    0.14
    ft
    0.14
    icens
    0.14
    rob
    0.13
    ardo
    0.13
    strap
    0.13
    ãĤ¦ãĥĪ
    0.13
    ottie
    0.13
    inerary
    0.13
    Activations Density 0.013%

    No Known Activations