INDEX

Explanations

elements related to food and cooking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

glas

-0.18

Éµ

-0.15

beth

-0.15

heit

-0.15

hlas

-0.14

 rekl

-0.14

atori

-0.14

Fus

-0.14

rub

-0.14

ango

-0.14

POSITIVE LOGITS

 including

0.20

 gá»ĵm

0.18

FIELDS

0.17

 INCLUDING

0.17

åĮħæĭ¬

0.17

.Compose

0.16

UPLE

0.16

 ÑģÐ¾ÑģÑĤÐ¾Ñı

0.16

including

0.15

 Including

0.15

Activations Density 0.539%

elements related to food and cooking

No Comments

No Known Activations