INDEX

Explanations

references to cancer and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

geh

-0.18

ledo

-0.16

phis

-0.15

tant

-0.15

_PLACE

-0.15

urement

-0.15

elite

-0.15

vio

-0.14

veh

-0.14

sert

-0.14

POSITIVE LOGITS

ous

0.40

ously

0.23

 cells

0.23

 cell

0.20

-cell

0.19

uous

0.18

ousel

0.18

moon

0.18

ogenesis

0.17

OUS

0.17

Activations Density 0.015%

references to cancer and related terms

No Comments

No Known Activations