INDEX

Explanations

content related to data collection and privacy policies

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

en

-0.15

à¸¨

-0.15

EN

-0.15

.fm

-0.15

Bon

-0.14

code

-0.14

Jac

-0.13

unj

-0.13

inki

-0.13

_constants

-0.13

POSITIVE LOGITS

elop

0.16

ordon

0.16

-Sah

0.15

ledon

0.15

auty

0.14

ercial

0.14

klad

0.14

aminer

0.14

Vig

0.14

stice

0.14

Activations Density 0.025%

content related to data collection and privacy policies

No Comments

No Known Activations