INDEX

Explanations

references to various categories or topics related to entertainment and personal interests

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

irts

-0.16

ìĸµ

-0.14

Ã¡Å¾

-0.14

iera

-0.14

pie

-0.14

orage

-0.14

gnore

-0.14

ared

-0.13

MBProgressHUD

-0.13

POSITIVE LOGITS

 relativ

0.15

acci

0.15

-posts

0.14

 Posts

0.14

REL

0.13

hill

0.13

/ns

0.13

aram

0.13

Err

0.13

Activations Density 0.014%

references to various categories or topics related to entertainment and personal interests

No Known Activations