Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 6-LLAMASCOPE-RES-32K
    6. 21564
    Prev
    Next
    INDEX
    Explanations

    terms associated with evasion or circumvention of rules or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utdown
    -0.16
    lesi
    -0.15
    utton
    -0.15
     å¾Ĵ
    -0.14
    otine
    -0.14
    /LICENSE
    -0.14
    SystemService
    -0.14
    é¼
    -0.14
    owl
    -0.13
    /hash
    -0.13
    POSITIVE LOGITS
    eniable
    0.15
     buck
    0.15
    doors
    0.15
    athe
    0.15
    sted
    0.15
    603
    0.15
    Ỽ
    0.14
     UNITY
    0.14
    agus
    0.14
    çĴĥ
    0.14
    Activations Density 0.031%

    No Known Activations