INDEX

Explanations

phrases related to statements of obligation, regulation, and enforcement

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

text describing things that were or came close to being in a particular state or condition, often using forms of "was" or "were" followed by descriptive phrases.

oai_token-act-pair · claude-4-5-sonnet

Triggered by @jyhe0408

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ego

-0.17

ãĥĲãĤ¤

-0.16

ear

-0.15

unga

-0.15

eba

-0.15

ASI

-0.15

abad

-0.14

ear

-0.14

olas

-0.14

emean

-0.14

POSITIVE LOGITS

uddle

0.16

DMA

0.16

UCT

0.15

æī±

0.14

unan

0.14

topic

0.14

udic

0.14

ÃĹ↵↵

0.14

aÄĩ

0.14

.componentInstance

0.14

Activations Density 0.360%

phrases related to statements of obligation, regulation, and enforcement

text describing things that were or came close to being in a particular state or condition, often using forms of "was" or "were" followed by descriptive phrases.

No Known Activations