© 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. 12-LLAMASCOPE-RES-32K
    6. 15291
    Prev
    Next
    INDEX
    Explanations

    terms related to classifications and conditions in various contexts, especially focusing on health, economic conditions, and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kou
    -0.16
    Ñıд
    -0.16
    kowski
    -0.16
    berger
    -0.14
     addTarget
    -0.14
    ORED
    -0.14
    lder
    -0.14
    Intialized
    -0.14
     رÙĩ
    -0.13
    printStats
    -0.13
    POSITIVE LOGITS
     Hayden
    0.14
    rescia
    0.14
     Fountain
    0.14
     Managed
    0.14
     Mixed
    0.13
     گرد
    0.13
     Misc
    0.13
    able
    0.13
    hoe
    0.13
     Anderson
    0.13
    Activations Density 0.074%

    No Known Activations