INDEX

Explanations

common pronouns and conjunctions indicative of informal speech or discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Fizz

-0.16

udoku

-0.16

 Garland

-0.15

 Stanley

-0.15

atra

-0.15

 Checkout

-0.14

rtl

-0.14

Ã¼hl

-0.14

ypass

-0.14

lsen

-0.14

POSITIVE LOGITS

ey

0.16

tro

0.15

fo

0.15

aris

0.15

ide

0.14

Tro

0.14

éĹ»

0.14

Tro

0.14

ides

0.13

 tack

0.13

Activations Density 0.003%

common pronouns and conjunctions indicative of informal speech or discourse

No Comments

No Known Activations