INDEX

Explanations

references to emotional experiences and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

amba

-0.17

uur

-0.16

ivery

-0.15

illage

-0.15

blr

-0.14

orial

-0.14

Ð¾Ð»Ð¾ÑĤ

-0.14

esel

-0.14

hva

-0.14

.shtml

-0.13

POSITIVE LOGITS

pell

0.18

ounder

0.18

dee

0.15

nek

0.14

urg

0.14

rain

0.14

ny

0.14

ni

0.14

Pago

0.14

Activations Density 0.012%

references to emotional experiences and well-being

No Comments

No Known Activations