INDEX

Explanations

instances of high-frequency words and specific terms related to personal experiences and emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Zag

-0.15

iesen

-0.15

oute

-0.14

Zem

-0.14

sty

-0.14

aina

-0.14

oner

-0.14

isa

-0.14

occo

-0.14

pton

-0.14

POSITIVE LOGITS

ensively

0.15

abilia

0.14

UpInside

0.14

çłĤ

0.14

 wheels

0.14

.BLL

0.14

ä¸Ī

0.14

 Jackson

0.14

oth

0.14

wner

0.14

Activations Density 0.002%

instances of high-frequency words and specific terms related to personal experiences and emotions

No Comments

No Known Activations