INDEX

Explanations

actions related to doing, performing tasks, and achieving goals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ð¾ÑıÑĤ

-0.16

coder

-0.15

#:

-0.14

.CurrentCulture

-0.13

inned

-0.13

Ã¤d

-0.13

'].'/

-0.13

æ´ŀ

-0.13

pcl

-0.13

POSITIVE LOGITS

 tasks

0.20

omba

0.20

 Tasks

0.18

inkel

0.17

arus

0.17

ueur

0.16

tasks

0.16

Tasks

0.16

-Ta

0.16

arial

0.15

Activations Density 0.073%

actions related to doing, performing tasks, and achieving goals

No Comments

No Known Activations