INDEX

Explanations

references to the name "Harris" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ts

-0.26

tf

-0.25

eer

-0.24

tm

-0.24

tas

-0.23

ti

-0.23

-0.22

haus

-0.22

ta

-0.22

POSITIVE LOGITS

(es

0.40

ness

0.23

0.22

’

0.22

dom

0.21

esModule

0.20

phere

0.20

ses

0.20

sing

0.20

ÙĨØ§ÙħÙĩ

0.19

Activations Density 0.314%

references to the name "Harris" and its variants

No Comments

No Known Activations