INDEX

Explanations

references to inclusive or comprehensive concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ovich

-0.18

-0.16

less

-0.16

offs

-0.16

jem

-0.15

yonel

-0.15

nde

-0.15

luck

-0.14

ors

-0.14

off

-0.14

POSITIVE LOGITS

igator

0.24

igators

0.19

endale

0.18

-purpose

0.17

ready

0.17

otre

0.17

uded

0.17

usion

0.16

ERGY

0.16

speed

0.16

Activations Density 0.057%

references to inclusive or comprehensive concepts

No Comments

No Known Activations