INDEX

Explanations

references to specific characters and interactions in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ulumi

-0.17

YPE

-0.16

 planta

-0.16

Î±Î¹

-0.16

ste

-0.15

uv

-0.15

èĥŀ

-0.14

"struct

-0.14

éĸĵãģ«

-0.13

 Bret

-0.13

POSITIVE LOGITS

 ones

0.18

 ideal

0.17

 Farr

0.16

ib

0.14

ĴĪ

0.14

 Nose

0.14

 accom

0.13

 neutral

0.13

exampleInputEmail

0.13

 extra

0.13

Activations Density 0.091%

references to specific characters and interactions in narratives

No Comments

No Known Activations