INDEX

Explanations

cooking instructions and techniques 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

idir

-0.17

antan

-0.16

 Ð¿Ð¾Ð·

-0.15

ngr

-0.15

alia

-0.15

hana

-0.15

nya

-0.14

ehir

-0.14

mnop

-0.14

Fol

-0.14

POSITIVE LOGITS

vo

0.16

vo

0.15

aurant

0.15

HEST

0.14

isk

0.14

 baise

0.14

 OVERRIDE

0.14

ìĿĮ

0.13

 imaginary

0.13

 conexao

0.13

Activations Density 0.024%

cooking instructions and techniques in recipes

No Comments

No Known Activations