INDEX

Explanations

references to data or statistics, particularly in relation to time and percentages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

obus

-0.16

uire

-0.15

PCR

-0.15

erd

-0.14

recent

-0.14

iller

-0.14

maz

-0.14

Ð¼Ð°Ð·

-0.14

 Recently

-0.14

amak

-0.14

POSITIVE LOGITS

stÃŃ

0.16

 inception

0.15

ABCDE

0.15

Sortable

0.15

 data

0.14

wing

0.14

 Raleigh

0.14

core

0.14

asc

0.14

Activations Density 0.060%

references to data or statistics, particularly in relation to time and percentages

No Comments

No Known Activations