INDEX

Explanations

the word "as" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

brook

-0.17

amp

-0.17

ailer

-0.17

ata

-0.17

 Misc

-0.15

uforia

-0.15

HF

-0.15

house

-0.14

 Juda

-0.14

lette

-0.14

POSITIVE LOGITS

propri

0.14

:host

0.14

Dut

0.14

toupper

0.14

reff

0.14

bounce

0.14

.registry

0.14

udem

0.13

udded

0.13

opup

0.13

Activations Density 0.015%

the word "as" used in various contexts

No Comments

No Known Activations