INDEX

Explanations

punctuation marks and quotation symbols 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

PCS

-0.17

edy

-0.17

theless

-0.14

Î¸Ïħ

-0.14

ALER

-0.14

haft

-0.14

 à¹Ĩ

-0.13

bre

-0.13

 Brexit

-0.13

oids

-0.13

POSITIVE LOGITS

olini

0.15

Ã¡c

0.14

ebi

0.14

ayi

0.14

ches

0.14

srp

0.14

nier

0.13

lesi

0.13

orning

0.13

oundation

0.13

Activations Density 0.064%

punctuation marks and quotation symbols within the text

No Comments

No Known Activations