INDEX

Explanations

references to kitchen utensils and cooking vessels used in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

egr

-0.15

ingu

-0.14

opus

-0.14

dro

-0.14

ÑĥÑĩÐ°

-0.14

æīĭ

-0.14

AtA

-0.14

 Baum

-0.14

hip

-0.13

POSITIVE LOGITS

 Lumpur

0.17

=-=-=-=-

0.16

 Gest

0.15

ÑĩÐ¸Ðº

0.15

mare

0.15

 Sunder

0.14

 Snowden

0.14

FORCE

0.14

nivel

0.14

æļ®

0.14

Activations Density 0.014%

references to kitchen utensils and cooking vessels used in recipes

No Comments

No Known Activations