INDEX

Explanations

references to the White House and its activities or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

nt

-0.16

AMES

-0.16

name

-0.15

athy

-0.15

nd

-0.15

nf

-0.15

uber

-0.14

size

-0.14

server

-0.14

uet

-0.14

POSITIVE LOGITS

hall

0.24

-collar

0.22

caps

0.21

legg

0.21

aker

0.20

hurst

0.20

-hot

0.19

 Plains

0.19

haven

0.19

head

0.19

Activations Density 0.013%

references to the White House and its activities or context

No Comments

No Known Activations