INDEX

Explanations

quotes or dialogue within 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 @ 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

regor

-0.17

uer

-0.16

ummy

-0.15

Kay

-0.15

acre

-0.15

hva

-0.14

way

-0.14

ather

-0.14

Kay

-0.14

uste

-0.13

POSITIVE LOGITS

edik

0.17

uls

0.16

elsey

0.15

Lint

0.15

vos

0.14

asa

0.14

/Internal

0.14

andid

0.14

Activations Density 0.045%

quotes or dialogue within the text

No Comments

No Known Activations