INDEX

Explanations

concepts related to exploration and discovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ukan

-0.16

ched

-0.16

aphore

-0.16

arkan

-0.15

.gdx

-0.15

inality

-0.15

IDO

-0.15

pire

-0.15

imals

-0.15

à¸¡

-0.14

POSITIVE LOGITS

arium

0.15

ä¸Ģä¸ĭ

0.14

rence

0.14

aniel

0.14

 depths

0.14

/ex

0.14

 Depths

0.14

 ways

0.13

-option

0.13

Activations Density 0.032%

concepts related to exploration and discovery

No Comments

No Known Activations