INDEX

Explanations

references to intention or attitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ð»Ð¸ÑĨ

-0.18

head

-0.18

onn

-0.18

abra

-0.17

off

-0.17

erie

-0.16

oy

-0.16

ons

-0.16

POSITIVE LOGITS

orney

0.28

itudes

0.27

Att

0.24

ENTION

0.24

orneys

0.23

itude

0.23

acker

0.22

anooga

0.20

acked

0.20

acks

0.20

Activations Density 0.013%

references to intention or attitude

No Comments

No Known Activations