INDEX

Explanations

actions or activities related to assistance and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

enaries

-0.17

df

-0.15

DF

-0.15

braco

-0.15

df

-0.15

istar

-0.15

TOM

-0.14

POSITIVE LOGITS

 drivers

0.24

 driver

0.22

 Drivers

0.22

 Driver

0.21

Drivers

0.21

-driver

0.21

driver

0.21

Driver

0.20

_driver

0.19

drivers

0.19

Activations Density 0.027%

actions or activities related to assistance and support

No Comments

No Known Activations