INDEX

Explanations

words related to rules and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

cca

-0.15

sta

-0.15

ling

-0.14

mand

-0.13

Loy

-0.13

essler

-0.13

 ÙģØ±

-0.13

Ã³j

-0.13

lm

-0.13

dro

-0.13

POSITIVE LOGITS

ofile

0.20

ottle

0.19

/legal

0.18

oenix

0.17

oton

0.15

ichick

0.15

ebi

0.14

lÃŃn

0.14

Ð¾ÑĤÐ¸

0.14

intl

0.14

Activations Density 0.027%

words related to rules and regulations

No Comments

No Known Activations