INDEX

Explanations

instances of the word "which" in various contexts

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

afil

-0.15

ENO

-0.14

rve

-0.14

Ø§Ø¨Ø¹

-0.14

beck

-0.14

ernet

-0.14

ileo

-0.13

emailer

-0.13

 epile

-0.13

POSITIVE LOGITS

 sake

0.27

 purposes

0.22

ays

0.17

 purpose

0.16

_queries

0.15

geries

0.15

.undefined

0.15

cing

0.15

unnable

0.15

Ã§a

0.14

Activations Density 0.089%

instances of the word "which" in various contexts

No Comments

No Known Activations