INDEX

Explanations

references to social interactions and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 entirety

-0.22

 upon

-0.16

 tumblr

-0.16

 ìĿ´ëĬĶ

-0.16

 snapchat

-0.16

 rubbish

-0.15

oric

-0.15

 typically

-0.15

ãģ¨ãģªãĤĭ

-0.15

 curated

-0.14

POSITIVE LOGITS

 everybody

0.17

 aggrav

0.17

sez

0.16

Everybody

0.16

nik

0.16

 real

0.16

 REAL

0.16

 Everybody

0.15

Naw

0.15

 anybody

0.15

Activations Density 2.254%

references to social interactions and relationships

No Comments

No Known Activations