INDEX

Explanations

punctuation marks, specifically periods and apostrophes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

athan

-0.16

Sortable

-0.15

ProgressHUD

-0.14

avo

-0.14

xcb

-0.14

upd

-0.14

 Latter

-0.13

throp

-0.13

ware

-0.13

rog

-0.13

POSITIVE LOGITS

izza

0.17

luet

0.17

arp

0.16

foy

0.14

 Together

0.14

TI

0.14

 addCriterion

0.14

.argument

0.14

null

0.14

OLON

0.14

Activations Density 0.001%

punctuation marks, specifically periods and apostrophes

No Comments

No Known Activations