INDEX

Explanations

expressions of gratitude and appreciation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

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

inned

-0.17

 Reporter

-0.15

unct

-0.14

esis

-0.14

_contin

-0.14

are

-0.13

arem

-0.13

æª

-0.13

_vendor

-0.13

tm

-0.13

POSITIVE LOGITS

ainen

0.16

vrd

0.15

erez

0.14

epad

0.14

 Resp

0.14

ìĦĿ

0.13

.lift

0.13

istrovstvÃŃ

0.13

 pornografia

0.13

agus

0.13

Activations Density 0.017%

expressions of gratitude and appreciation

No Known Activations