INDEX

Explanations

references to "slices" 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

WER

-0.16

 arada

-0.15

Pur

-0.15

adera

-0.14

ise

-0.14

oned

-0.14

oug

-0.14

oted

-0.14

SSIP

-0.14

 insist

-0.14

POSITIVE LOGITS

ÐµÑĢÐ¿

0.19

precated

0.16

ombat

0.15

ÐµÐºÑĤ

0.15

Ã±ana

0.15

eyh

0.15

zew

0.14

ëŀµ

0.14

/cop

0.14

christ

0.14

Activations Density 0.012%

references to "slices" in various contexts

No Comments

No Known Activations

references to "slices" in various contexts

No Comments

No Known Activations