INDEX

Explanations

keywords and phrases related to popular television shows and their elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

iesen

-0.17

onse

-0.16

amble

-0.16

igham

-0.15

 Traverse

-0.14

 Rover

-0.14

HexString

-0.14

 Pound

-0.14

inox

-0.14

ennes

-0.14

POSITIVE LOGITS

aeda

0.20

oment

0.16

 Contributors

0.15

incer

0.15

ument

0.15

itness

0.15

orry

0.14

Hv

0.14

ystate

0.14

 Meadows

0.14

Activations Density 0.009%

keywords and phrases related to popular television shows and their elements

No Comments

No Known Activations