INDEX

Explanations

instances of the word "all" 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ovich

-0.17

edom

-0.16

zept

-0.15

antium

-0.15

 bitten

-0.14

ÙĨÙħ

-0.14

ze

-0.14

venes

-0.14

elsing

-0.14

guild

-0.13

POSITIVE LOGITS

 Pere

0.15

Ãłu

0.15

 Ellis

0.14

/remove

0.14

rub

0.14

 Peters

0.14

LLLL

0.14

acket

0.14

rub

0.14

 Koch

0.13

Activations Density 0.008%

instances of the word "all" in various contexts

No Comments

No Known Activations