© 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. 17-LLAMASCOPE-RES-32K
    11. 12348
    Prev
    Next
    INDEX
    Explanations

    topics related to environmental and societal concerns, particularly in the context of hunting, health, and community spaces

    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
    .Executor
    -0.15
    noinspection
    -0.14
    bidden
    -0.13
    landa
    -0.13
     yap
    -0.13
    oug
    -0.13
    htag
    -0.13
     Ping
    -0.12
    ÑĢеÑĪ
    -0.12
    anco
    -0.12
    POSITIVE LOGITS
     дво
    0.15
     å¾ĴæŃ©
    0.15
    pollo
    0.14
    ioned
    0.14
    TestingModule
    0.14
    uye
    0.14
    :;↵
    0.13
    using
    0.13
    .onViewCreated
    0.13
    sys
    0.13
    Activations Density 0.005%

    No Known Activations