INDEX

Explanations

important terms related to roles, functions, and specific actions within structured environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

equ

-0.16

ICA

-0.16

iÄħ

-0.15

unami

-0.14

 Hend

-0.14

à¸±à¸Ļà¸ģ

-0.13

cha

-0.13

 sÃ¡t

-0.13

.variables

-0.13

uy

-0.13

POSITIVE LOGITS

\Id

0.18

.scalablytyped

0.15

iyat

0.15

vey

0.14

elper

0.14

byname

0.14

.extension

0.14

uffle

0.14

Activations Density 0.010%

important terms related to roles, functions, and specific actions within structured environments

No Comments

No Known Activations