INDEX

Explanations

repetitive phrases emphasizing the word "every."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

eworthy

-0.16

 Ekim

-0.15

ermen

-0.14

alone

-0.14

icken

-0.14

_WP

-0.14

 Briggs

-0.13

æ¥Ń

-0.13

mgr

-0.13

POSITIVE LOGITS

-other

0.15

ody

0.15

thin

0.15

odyn

0.15

ones

0.14

ayah

0.14

hone

0.14

though

0.14

Ħìŀ¬

0.14

every

0.14

Activations Density 0.040%

repetitive phrases emphasizing the word "every."

No Comments

No Known Activations