INDEX

Explanations

adjectives describing extremity or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

os

-0.17

iolet

-0.17

ory

-0.17

aje

-0.15

ager

-0.15

AGER

-0.15

uffle

-0.15

LEASE

-0.14

zon

-0.14

POSITIVE LOGITS

eyse

0.19

sworth

0.17

veis

0.16

isay

0.15

esis

0.15

duto

0.14

psz

0.14

cko

0.14

ghan

0.14

ieder

0.14

Activations Density 0.001%

adjectives describing extremity or intensity

No Comments

No Known Activations