INDEX

Explanations

references to "view" 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

View

-0.16

ceso

-0.15

readcr

-0.15

ileo

-0.15

isle

-0.15

utex

-0.14

fos

-0.14

åĳ³

-0.14

buie

-0.14

Model

-0.14

POSITIVE LOGITS

finder

0.32

shed

0.28

ports

0.27

able

0.25

pager

0.25

topic

0.25

ings

0.25

point

0.23

ability

0.21

.OnClickListener

0.21

Activations Density 0.053%

references to "view" in various contexts

No Comments

No Known Activations