Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 31022
    Prev
    Next
    INDEX
    Explanations

    instances of the word "come" and various forms of arrival or attendance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayer
    -0.15
     bef
    -0.15
    ience
    -0.15
    еÑİ
    -0.15
    AYER
    -0.14
    endor
    -0.14
    urer
    -0.14
     numbered
    -0.14
    εÏģι
    -0.14
    ustos
    -0.14
    POSITIVE LOGITS
    KHR
    0.18
    roma
    0.15
    åĦĢ
    0.15
    Gran
    0.15
    iators
    0.15
    ÙĪØ°
    0.14
    iyle
    0.14
     Gran
    0.14
     gran
    0.14
    arily
    0.14
    Activations Density 0.121%

    No Known Activations