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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-LLAMASCOPE-RES-32K
    6. 15840
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal possession and related charges of controlled substances and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lfw
    -0.19
    lex
    -0.17
    ixin
    -0.15
    PLOY
    -0.15
    евиÑĩ
    -0.14
    643
    -0.14
    cth
    -0.14
    esModule
    -0.14
    commended
    -0.14
    \<^
    -0.14
    POSITIVE LOGITS
    lichkeit
    0.16
    ularity
    0.15
    indh
    0.15
     Massive
    0.14
    æĻ
    0.14
     fans
    0.14
    Bob
    0.14
    ushi
    0.14
    111
    0.14
    ansa
    0.14
    Activations Density 0.014%

    No Known Activations