INDEX

Explanations

expressions related to social interconnectedness and personal accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ono

-0.17

yll

-0.15

icas

-0.15

illa

-0.15

emer

-0.14

 McMahon

-0.14

mac

-0.14

lic

-0.14

uzzi

-0.14

markup

-0.14

POSITIVE LOGITS

 Krish

0.19

Ved

0.17

 Freddy

0.15

vÃ¡

0.15

plit

0.14

idity

0.14

ponse

0.14

__$

0.14

clave

0.14

ware

0.14

Activations Density 0.006%

expressions related to social interconnectedness and personal accountability

No Comments

No Known Activations