INDEX

Explanations

references to pop culture

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 proposition

-0.15

break

-0.15

anmar

-0.14

utom

-0.14

ÑĢÐ°Ð²Ð°

-0.14

iox

-0.13

Ã©g

-0.13

cling

-0.13

ubi

-0.13

 Cutter

-0.13

POSITIVE LOGITS

0.16

ÑĮÐµ

0.14

SCN

0.14

omba

0.14

aney

0.14

 Shea

0.14

ocup

0.13

 Vince

0.13

esc

0.13

iteli

0.13

Activations Density 0.012%

references to pop culture

No Comments

No Known Activations