INDEX

Explanations

phrases related to personal choices and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

skyt

-0.17

erate

-0.17

.scalablytyped

-0.16

ellar

-0.16

foon

-0.16

$MESS

-0.15

LB

-0.15

iline

-0.14

OTTOM

-0.14

Generation

-0.14

POSITIVE LOGITS

 bail

0.15

 Bryce

0.14

lich

0.14

UIScreen

0.14

.modules

0.14

ant

0.14

ixo

0.14

-byte

0.13

erten

0.13

Activations Density 0.107%

phrases related to personal choices and actions

No Comments

No Known Activations