INDEX

Explanations

expressions of admiration or appreciation for qualities or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 yours

-0.15

lesh

-0.14

 Lucas

-0.14

 Ð¿Ð¾Ñħ

-0.14

uin

-0.13

ges

-0.13

uct

-0.13

laws

-0.13

atatype

-0.13

POSITIVE LOGITS

its

0.22

Its

0.18

its

0.18

Its

0.17

ecz

0.16

 fact

0.16

Ã¼gen

0.16

ugen

0.15

how

0.15

 aspect

0.15

Activations Density 0.125%

expressions of admiration or appreciation for qualities or experiences

No Comments

No Known Activations