INDEX

Explanations

gerunds and present participles that indicate actions

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

rix

-0.15

(cf

-0.15

olver

-0.15

phin

-0.14

owell

-0.14

Ð¾Ð²Ð°ÑĢ

-0.14

rong

-0.14

obra

-0.13

oltage

-0.13

amac

-0.13

POSITIVE LOGITS

cakes

0.16

Bond

0.14

bond

0.14

staking

0.14

-placeholder

0.14

 Demir

0.14

lint

0.13

ado

0.13

Ð°Ð»ÑĮ

0.13

 Orig

0.13

Activations Density 0.137%

gerunds and present participles that indicate actions

No Comments

No Known Activations