INDEX

Explanations

the article "an"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ø±ÙĪÙģ

-0.16

asurer

-0.16

quent

-0.16

svp

-0.16

_ioctl

-0.16

ipes

-0.15

iazza

-0.15

gth

-0.15

urm

-0.15

 Patron

-0.14

POSITIVE LOGITS

 Harm

0.17

 prompt

0.17

0.16

ecs

0.16

().'/

0.16

::__

0.15

lak

0.15

nap

0.15

nak

0.14

Ð°ÑĢÐ°Ð¼

0.14

Activations Density 0.008%

the article "an"

No Comments

No Known Activations