INDEX

Explanations

instances of the word "watch" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ittest

-0.16

ured

-0.15

veau

-0.15

antino

-0.15

äº

-0.15

Matcher

-0.15

cts

-0.14

ULATE

-0.14

Calibri

-0.14

utter

-0.14

POSITIVE LOGITS

tower

0.18

 lique

0.15

elper

0.15

apers

0.15

ÅŁehir

0.15

Dog

0.14

bul

0.14

aper

0.14

0.13

Activations Density 0.033%

instances of the word "watch" and its variations

No Comments

No Known Activations