INDEX

Explanations

names and characteristics of various plants and herbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.16

ugi

-0.16

-0.14

sgi

-0.14

 Cran

-0.14

æĴ®

-0.14

sto

-0.13

_DM

-0.13

 Childhood

-0.13

POSITIVE LOGITS

 trees

0.23

-growing

0.21

 growing

0.20

trees

0.20

 grown

0.18

 bushes

0.18

æłĳ

0.17

 seed

0.17

 Growing

0.17

agine

0.16

Activations Density 0.142%

names and characteristics of various plants and herbs

No Comments

No Known Activations