INDEX

Explanations

references to total quantities or universal concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

TargetException

-0.18

olla

-0.17

ucz

-0.14

uset

-0.14

ıa

-0.14

zes

-0.14

amespace

-0.14

Ðħ

-0.14

Qed

-0.14

phinx

-0.14

POSITIVE LOGITS

 ActionTypes

0.16

EEK

0.15

lich

0.15

Tam

0.14

cov

0.14

van

0.14

to

0.14

liv

0.14

null

0.13

Activations Density 0.011%

references to total quantities or universal concepts

No Comments

No Known Activations