INDEX

Explanations

past participle forms of verbs, particularly those that imply an action or a process that has been completed

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Î³Î¿

-0.15

ertas

-0.14

enz

-0.14

Wunused

-0.14

anuts

-0.14

otel

-0.13

 tinh

-0.13

unte

-0.13

andez

-0.13

anine

-0.13

POSITIVE LOGITS

ampo

0.14

tractor

0.14

idders

0.14

uyu

0.13

unj

0.13

oleon

0.13

amp

0.13

ysis

0.13

.lift

0.13

ness

0.13

Activations Density 0.275%

past participle forms of verbs, particularly those that imply an action or a process that has been completed

No Comments

No Known Activations