© 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. 6147
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific character or symbol used for various purposes in the text

    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
    onium
    -0.15
    ÙĦÙĩ
    -0.15
    ium
    -0.14
    eci
    -0.14
    ulle
    -0.14
    dataType
    -0.13
    ollapse
    -0.13
    اÙĬر
    -0.13
    zh
    -0.13
    inalg
    -0.13
    POSITIVE LOGITS
    hton
    0.20
    Previous
    0.18
    orget
    0.15
    ograd
    0.15
    385
    0.15
     Giang
    0.14
     intuition
    0.14
    precated
    0.14
    asma
    0.14
    previous
    0.14
    Activations Density 0.011%

    No Known Activations