INDEX

Explanations

punctuation marks and formatting elements in written text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

.dm

-0.15

DMI

-0.15

agh

-0.14

?q

-0.14

osate

-0.14

NOWLED

-0.14

isty

-0.14

/session

-0.14

ologne

-0.14

UCT

-0.13

POSITIVE LOGITS

uchos

0.16

0.15

akov

0.15

_internal

0.15

Div

0.15

ant

0.14

lick

0.14

 Daniels

0.14

div

0.14

alus

0.14

Activations Density 0.001%

punctuation marks and formatting elements in written text

No Comments

No Known Activations