INDEX

Explanations

programming-related terms, particularly related to C++

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugg

-0.16

irector

-0.15

 rain

-0.15

yne

-0.15

ikan

-0.15

CJK

-0.15

veloper

-0.14

íĽĪ

-0.14

 tiÃªn

-0.14

adian

-0.14

POSITIVE LOGITS

 Valle

0.16

mens

0.16

bla

0.15

lesc

0.15

Sle

0.14

loy

0.14

iene

0.13

mere

0.13

 buurt

0.13

 Mons

0.13

Activations Density 0.020%

programming-related terms, particularly related to C++

No Comments

No Known Activations