INDEX

Explanations

punctuation and formatting elements, particularly periods and common signaling words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

istar

-0.18

ç¦

-0.17

-0.16

inois

-0.16

idel

-0.15

erchant

-0.14

amarin

-0.14

nut

-0.14

ced

-0.14

amiliar

-0.14

POSITIVE LOGITS

enza

0.14

ģn

0.14

\common

0.14

Ð¾ÑģÑĥÐ´

0.14

MMM

0.14

fir

0.14

åĿĤ

0.13

Ø§Ø¨Ø·

0.13

.ctx

0.13

 NÄĽkterÃ¡

0.13

Activations Density 0.000%

punctuation and formatting elements, particularly periods and common signaling words

No Comments

No Known Activations