INDEX

Explanations

references to movies and film-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

.LoggerFactory

-0.20

ively

-0.18

ìĦľëĬĶ

-0.17

nn

-0.15

err

-0.15

ings

-0.15

rib

-0.14

most

-0.14

ages

-0.14

POSITIVE LOGITS

go

0.26

clip

0.20

-length

0.19

guide

0.18

gue

0.18

going

0.18

buff

0.18

 trailers

0.17

/mp

0.17

/show

0.16

Activations Density 0.023%

references to movies and film-related content

No Comments

No Known Activations