INDEX

Explanations

punctuation and the word 'and' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

artic

-0.15

.tp

-0.14

altern

-0.13

 Petty

-0.13

 Gambling

-0.13

PREC

-0.13

 Truly

-0.13

Whe

-0.13

atre

-0.13

.preferences

-0.13

POSITIVE LOGITS

AdapterFactory

0.15

-urlencoded

0.14

isha

0.14

å¥´

0.14

ipay

0.14

 constructive

0.13

ibox

0.13

Ø®Ø´

0.13

onio

0.13

igu

0.13

Activations Density 0.063%

punctuation and the word 'and' in various contexts

No Comments

No Known Activations