INDEX

Explanations

punctuation marks, particularly commas and colons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

gers

-0.15

affle

-0.14

æīĢ

-0.14

dig

-0.14

emento

-0.13

oud

-0.13

ÑĹ

-0.13

urs

-0.13

PB

-0.13

.ascii

-0.13

POSITIVE LOGITS

OfWork

0.17

tram

0.15

SWEP

0.15

Ð¾ÑĤÑĢÐµÐ±

0.15

lej

0.14

ekli

0.14

.DefaultCellStyle

0.14

stown

0.14

olin

0.14

\CMS

0.13

Activations Density 0.057%

punctuation marks, particularly commas and colons

No Comments

No Known Activations