INDEX

Explanations

capitalization and the term "cap" 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ymph

-0.18

Ð¸Ð¼Ñĥ

-0.17

hound

-0.16

ees

-0.16

 __("

-0.16

prene

-0.15

eyin

-0.15

TRL

-0.15

ee

-0.15

bracht

-0.15

POSITIVE LOGITS

itol

0.34

illary

0.31

ric

0.31

stone

0.29

itulo

0.26

rice

0.26

ÃŃtulo

0.25

stan

0.25

ella

0.25

gem

0.24

Activations Density 0.016%

capitalization and the term "cap" in various contexts

No Comments

No Known Activations