INDEX

Explanations

occurrences of punctuation marks and indicators of structural breaks in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ibel

-0.18

ices

-0.17

éĺ³

-0.15

yer

-0.15

udio

-0.15

.eclipse

-0.14

locator

-0.14

Î´ÏĮ

-0.14

oundingBox

-0.14

ickerView

-0.14

POSITIVE LOGITS

 resent

0.16

ine

0.15

arez

0.14

 Covenant

0.14

/stdc

0.14

Ø³Ø±

0.14

_legacy

0.14

aky

0.14

utan

0.14

erna

0.14

Activations Density 0.000%

occurrences of punctuation marks and indicators of structural breaks in text

No Comments

No Known Activations