INDEX

Explanations

mentions of the word "post" throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

addin

-0.16

-0.14

vey

-0.14

_cond

-0.13

egg

-0.13

Ã©lÃ©

-0.13

ãĥĭãĥĥãĤ¯

-0.13

profit

-0.13

xc

-0.13

zt

-0.13

POSITIVE LOGITS

Å¡ek

0.18

emark

0.15

.mousePosition

0.15

serter

0.15

Äįek

0.14

assi

0.14

coe

0.14

æ°ı

0.14

apon

0.14

å¥

0.14

Activations Density 0.015%

mentions of the word "post" throughout the text

No Comments

No Known Activations