INDEX

Explanations

punctuation marks and their contextual usage

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

Jer

-0.15

ride

-0.14

ument

-0.14

consin

-0.14

ivil

-0.14

adb

-0.14

con

-0.14

ayne

-0.13

awesome

-0.13

POSITIVE LOGITS

å¤ªéĥİ

0.15

ë§¨

0.14

CastException

0.14

elerik

0.14

iam

0.14

duk

0.14

ibbon

0.13

_FLAG

0.13

.ham

0.13

.REG

0.13

Activations Density 0.307%

punctuation marks and their contextual usage

No Comments

No Known Activations