INDEX

Explanations

pronouns and their associated subjects in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

æħ

-0.15

ÐµÑĩ

-0.15

@stop

-0.15

Ð²Ð¾Ð»Ñı

-0.14

jar

-0.14

isman

-0.14

DLC

-0.14

PageRoute

-0.14

awe

-0.14

riz

-0.14

POSITIVE LOGITS

inde

0.17

 mÃ´n

0.15

otos

0.14

ertino

0.14

 bá»Ļ

0.14

dep

0.14

uzzer

0.13

OSE

0.13

lian

0.13

conj

0.13

Activations Density 0.189%

pronouns and their associated subjects in various contexts

No Comments

No Known Activations