INDEX

Explanations

phrases related to improvement, success, and system optimization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

adar

-0.16

USA

-0.15

inite

-0.14

bine

-0.14

ype

-0.14

adas

-0.13

hr

-0.13

ØºØ±

-0.13

htar

-0.13

 gren

-0.13

POSITIVE LOGITS

eza

0.15

_Execute

0.14

itur

0.14

 ná»¯a

0.14

sem

0.13

ouro

0.13

iaux

0.13

ntax

0.13

 contentValues

0.13

STALL

0.13

Activations Density 0.204%

phrases related to improvement, success, and system optimization

No Comments

No Known Activations