INDEX

Explanations

gerunds and present participles that indicate actions or ongoing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

enko

-0.17

vince

-0.16

 Disc

-0.15

icopt

-0.15

ancel

-0.14

zd

-0.14

cano

-0.14

prev

-0.14

qing

-0.14

nad

-0.14

POSITIVE LOGITS

:view

0.16

AlgorithmException

0.15

alker

0.15

ades

0.15

RIC

0.15

redients

0.14

oria

0.13

eyed

0.13

-commit

0.13

ieg

0.13

Activations Density 0.856%

gerunds and present participles that indicate actions or ongoing processes

No Comments

No Known Activations