INDEX

Explanations

names of people and references to television series

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

unami

-0.15

 Thing

-0.14

 Sanity

-0.14

_gateway

-0.13

ongo

-0.13

arios

-0.13

 Kash

-0.13

POSITIVE LOGITS

tvb

0.27

 mainland

0.18

incy

0.17

orthand

0.17

èī

0.17

ATV

0.17

QQ

0.17

 Milky

0.16

 Cant

0.16

QQ

0.16

Activations Density 0.023%

names of people and references to television series

No Comments

No Known Activations