INDEX

Explanations

punctuation marks and their varied uses within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

brtc

-0.17

 Garn

-0.15

zel

-0.14

erti

-0.14

oldt

-0.14

ussy

-0.14

olated

-0.14

ç¶Ń

-0.13

 knull

-0.13

otel

-0.13

POSITIVE LOGITS

0.16

atz

0.15

iso

0.14

Ð¾ÐºÐ¾Ð½

0.14

pite

0.14

urette

0.14

reso

0.14

@dynamic

0.14

iom

0.14

Activations Density 0.027%

punctuation marks and their varied uses within the text

No Comments

No Known Activations