© 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. 16-LLAMASCOPE-RES-32K
    11. 20663
    Prev
    Next
    INDEX
    Explanations

    terms, phrases, and descriptions related to horror themes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TMPro
    -0.17
    kits
    -0.15
    -bodied
    -0.15
    _MAXIMUM
    -0.15
    .Async
    -0.14
    аÑģÑĤи
    -0.14
    åĭĻ
    -0.13
    estruction
    -0.13
    son
    -0.13
    [color
    -0.13
    POSITIVE LOGITS
    gram
    0.20
    365
    0.17
    grams
    0.16
    ECTOR
    0.16
    ADX
    0.15
    -real
    0.15
    ÛĮدÙĩ
    0.15
    ANNEL
    0.15
    æĢĸ
    0.15
     lean
    0.14
    Activations Density 0.053%

    No Known Activations