INDEX

Explanations

instances of the word "overhe" (and variations involving "he" and "rehe")

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

-0.25

-0.20

-0.19

ss

-0.18

la

-0.17

sg

-0.17

elop

-0.17

nin

-0.17

POSITIVE LOGITS

aring

0.25

oric

0.24

ated

0.24

uristic

0.23

ating

0.23

arts

0.22

ctic

0.22

aven

0.21

arsed

0.21

aling

0.20

Activations Density 0.015%

instances of the word "overhe" (and variations involving "he" and "rehe")

No Comments

No Known Activations