INDEX

Explanations

instances of the preposition "to" 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

uit

-0.16

uition

-0.15

abouts

-0.15

ONUS

-0.15

leton

-0.15

apore

-0.14

ovu

-0.14

cela

-0.14

cosa

-0.14

uye

-0.14

POSITIVE LOGITS

 quote

0.29

say

0.25

 borrow

0.25

 varying

0.25

 coin

0.24

 paraph

0.23

me

0.23

wit

0.21

onces

0.21

be

0.20

Activations Density 0.031%

instances of the preposition "to" in various contexts

No Comments

No Known Activations