INDEX

Explanations

second-person pronouns and their corresponding actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ð¸Ð½Ð¾Ð²

-0.16

ÑģÑĭÐ»ÐºÐ¸

-0.16

atsby

-0.16

ÐµÑĢÑĮ

-0.15

aida

-0.15

utow

-0.15

ÑıÐ±

-0.15

esper

-0.14

ipay

-0.14

Î´Î¿

-0.14

POSITIVE LOGITS

tph

0.16

hare

0.15

 Oswald

0.15

my

0.14

ÏģÎµ

0.13

 turb

0.13

 manufacture

0.13

Eck

0.13

-t

0.13

rey

0.13

Activations Density 0.153%

second-person pronouns and their corresponding actions or states

No Comments

No Known Activations

second-person pronouns and their corresponding actions or states

No Comments

No Known Activations