INDEX

Explanations

references to bots and their impact on various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

tte

-0.20

aires

-0.18

versible

-0.17

tÃŃ

-0.16

orie

-0.16

umont

-0.16

alborg

-0.15

arious

-0.15

bine

-0.15

hurst

-0.15

POSITIVE LOGITS

nj

0.17

ÙĦØ§Ùģ

0.17

swana

0.15

erval

0.14

.Options

0.14

ATAB

0.14

warm

0.13

Î¸ÎµÏģ

0.13

ke

0.13

{/*

0.13

Activations Density 0.010%

references to bots and their impact on various contexts

No Comments

No Known Activations