INDEX

Explanations

API-related authentication terms and user roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iner

-0.19

ebek

-0.17

itters

-0.16

theless

-0.15

ulan

-0.15

äºĴ

-0.15

chyb

-0.14

uala

-0.14

mute

-0.14

 genders

-0.14

POSITIVE LOGITS

_TI

0.14

 Clair

0.14

andler

0.14

ermo

0.14

 athletic

0.14

ìĨĶ

0.14

0.13

gii

0.13

utc

0.13

 æ¨

0.13

Activations Density 0.023%

API-related authentication terms and user roles

No Comments

No Known Activations