INDEX

Explanations

variations of the letter 'k' in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

outines

-0.16

-0.14

letes

-0.14

ford

-0.14

ium

-0.14

ainers

-0.14

_UNUSED

-0.14

Ø§ÙĩØ¯

-0.14

ice

-0.14

ician

-0.14

POSITIVE LOGITS

inks

0.22

iosk

0.21

appa

0.17

essenger

0.17

:k

0.16

INET

0.16

nowledge

0.16

*k

0.16

cen

0.15

Activations Density 0.050%

variations of the letter 'k' in different contexts

No Comments

No Known Activations