INDEX

Explanations

references to photographs and photo-taking activities

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

áº£i

-0.15

 Rating

-0.14

íĶ½

-0.14

 rating

-0.14

ÐµÐ»ÑĮÐ·Ñı

-0.14

deg

-0.14

 Constantin

-0.14

aining

-0.14

Ð»ÐµÑĢ

-0.13

 Ratings

-0.13

POSITIVE LOGITS

 Vance

0.15

_activ

0.14

íĭ

0.14

.Layout

0.13

usk

0.13

ibbon

0.13

 Album

0.13

®

0.13

orative

0.13

Taken

0.13

Activations Density 0.035%

references to photographs and photo-taking activities

No Comments

No Known Activations