INDEX

Explanations

phrases related to availability and access to resources or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ationToken

-0.17

uento

-0.15

ares

-0.15

ong

-0.15

ffe

-0.14

ongan

-0.14

åºĬ

-0.14

ales

-0.14

.mul

-0.13

ilig

-0.13

POSITIVE LOGITS

ibly

0.26

ibilities

0.19

ions

0.17

nist

0.16

sed

0.16

_rights

0.15

Ð½Ð¾ÑģÑĤÑĮ

0.15

yonel

0.14

erif

0.14

roje

0.14

Activations Density 0.052%

phrases related to availability and access to resources or information

No Comments

No Known Activations