© 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. 17-LLAMASCOPE-RES-32K
    6. 26400
    Prev
    Next
    INDEX
    Explanations

    legal concepts related to claims, arguments, and corporate regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    704
    -0.15
    pers
    -0.14
    ÅĪ
    -0.14
    acomment
    -0.14
    ilon
    -0.14
    ancel
    -0.13
     honors
    -0.13
    crast
    -0.12
    ifs
    -0.12
    quier
    -0.12
    POSITIVE LOGITS
    ï¼īãģ¯
    0.29
    ")!=
    0.24
    ")==
    0.24
    åŃIJãģ¯
    0.22
    人ãģ¯
    0.20
    "is
    0.20
    )ìĿĢ
    0.20
     may
    0.20
    )ëĬĶ
    0.19
     will
    0.19
    Activations Density 1.471%

    No Known Activations