INDEX

Explanations

occurrences of the letter 'D' 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

addy

-0.17

Ð°Ñİ

-0.17

elta

-0.16

Å¡i

-0.16

awn

-0.16

emo

-0.15

ayo

-0.15

OWN

-0.15

ansa

-0.15

ÑĢÑĥÐ³

-0.15

POSITIVE LOGITS

yer

0.25

zure

0.24

lug

0.24

rey

0.24

ill

0.23

alg

0.22

oh

0.22

zial

0.22

uf

0.21

sou

0.21

Activations Density 0.028%

occurrences of the letter 'D' in various contexts

No Comments

No Known Activations