INDEX

Explanations

sequences of repeated characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 milfs

-0.17

-www

-0.14

auce

-0.14

à¸Ĭà¸²à¸ķ

-0.14

ARS

-0.14

rede

-0.14

éļĽ

-0.14

iller

-0.13

iesen

-0.13

bury

-0.13

POSITIVE LOGITS

kea

0.15

ena

0.15

ette

0.15

0.14

orno

0.14

../../../

0.14

ĩ

0.14

etto

0.14

etter

0.14

Mixin

0.14

Activations Density 0.003%

sequences of repeated characters or symbols

No Comments

No Known Activations