INDEX

Explanations

references to novels and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

aan

-0.18

yonel

-0.17

yor

-0.17

fully

-0.16

wards

-0.16

ed

-0.15

alom

-0.14

ASHBOARD

-0.14

fulness

-0.14

POSITIVE LOGITS

ty

0.24

ized

0.22

-length

0.21

ization

0.20

istic

0.20

lette

0.20

ised

0.19

izations

0.18

ize

0.17

iembre

0.17

Activations Density 0.012%

references to novels and literary works

No Comments

No Known Activations