INDEX

Explanations

punctuation marks and their variations, particularly focusing on periods and exclamation points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 ever

-0.15

agon

-0.14

avier

-0.14

ÙĨØ¯ÙĤ

-0.13

onaut

-0.13

 resin

-0.13

ometrics

-0.13

Apt

-0.13

ir

-0.13

 draft

-0.13

POSITIVE LOGITS

eneg

0.15

etc

0.15

Ð¾Ð½ÑĮ

0.14

ogle

0.13

.camel

0.13

erable

0.13

mente

0.13

sink

0.13

.CreateIndex

0.13

_migration

0.13

Activations Density 0.261%

punctuation marks and their variations, particularly focusing on periods and exclamation points

No Comments

No Known Activations