INDEX

Explanations

occurrences of the word "ga"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 McKay

-0.18

habi

-0.16

igi

-0.15

ior

-0.15

hap

-0.15

[section

-0.15

EGA

-0.15

McB

-0.15

 pháº©m

-0.15

POSITIVE LOGITS

ainted

0.16

amilia

0.15

alink

0.15

ftime

0.14

zek

0.14

ÑĨÐ²ÐµÑĤ

0.14

ENCHMARK

0.14

Ð´ÐµÐ¼

0.13

.spotify

0.13

 preferably

0.13

Activations Density 0.001%

occurrences of the word "ga"

No Comments

No Known Activations