INDEX

Explanations

mentions of duration indicators or references to time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

$MESS

-0.18

/trunk

-0.14

fabs

-0.14

utar

-0.14

yard

-0.14

way

-0.14

arming

-0.14

yards

-0.14

erde

-0.13

etter

-0.13

POSITIVE LOGITS

row

0.49

-row

0.37

Row

0.36

row

0.35

Row

0.35

.row

0.34

_row

0.34

ROW

0.33

ROW

0.31

row

0.31

Activations Density 0.017%

mentions of duration indicators or references to time periods

No Comments

No Known Activations