INDEX

Explanations

key statistical or numerical information

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

imar

-0.17

markup

-0.15

abcdefghijklmnop

-0.15

emem

-0.15

mk

-0.14

mil

-0.14

amar

-0.14

marvin

-0.14

hPa

-0.13

imbus

-0.13

POSITIVE LOGITS

1.25

0.77

ÂłM

0.67

 Ùħ

0.65

 Ðľ

0.61

.getM

0.60

:M

0.54

_m

0.54

.M

0.54

=M

0.54

Activations Density 0.287%

key statistical or numerical information

No Comments

No Known Activations