INDEX

Explanations

punctuation marks and their frequency 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

arkan

-0.18

owell

-0.16

 authDomain

-0.15

gens

-0.15

ursal

-0.15

offsetof

-0.14

nze

-0.14

ofire

-0.14

ourg

-0.14

kla

-0.14

POSITIVE LOGITS

avia

0.15

_TICK

0.14

Gri

0.14

 Sidney

0.13

ethe

0.13

uits

0.13

keepers

0.13

 Rudy

0.13

ancial

0.13

0.12

Activations Density 0.051%

punctuation marks and their frequency within the text

No Comments

No Known Activations