INDEX

Explanations

phrases related to pressure applied to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

AWN

-0.17

CGColor

-0.16

olland

-0.16

 plÃ¡

-0.15

Ð¼Ð°Ñħ

-0.15

ckett

-0.14

Ã¸d

-0.14

å¤©åłĤ

-0.14

ANGE

-0.14

egen

-0.14

POSITIVE LOGITS

raz

0.16

chwitz

0.16

isoner

0.15

emics

0.15

roupon

0.14

_MSB

0.14

PCP

0.14

owi

0.14

onom

0.14

Activations Density 0.107%

phrases related to pressure applied to individuals or entities

No Comments

No Known Activations