INDEX

Explanations

instances of the word "intrigue" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Sho

-0.15

anda

-0.14

ISMATCH

-0.14

imdi

-0.14

aphore

-0.14

icus

-0.14

INVAL

-0.13

Ð±Ð¸ÑĤ

-0.13

osti

-0.13

abad

-0.13

POSITIVE LOGITS

Ø·Ø±

0.15

sey

0.15

 Ð¼Ð¾Ð³

0.14

 sáºµn

0.14

CALE

0.14

Å¾il

0.14

fft

0.14

æº

0.14

½æķ°

0.14

Ã¼Ã§Ã¼k

0.14

Activations Density 0.005%

instances of the word "intrigue" and its variations

No Comments

No Known Activations