INDEX

Explanations

various references to "schemes."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lee

-0.17

ne

-0.17

oma

-0.16

falls

-0.16

ree

-0.15

ainen

-0.15

achi

-0.15

 thÆ°Æ¡ng

-0.15

ComputedStyle

-0.15

se

-0.15

POSITIVE LOGITS

emento

0.17

pered

0.16

atics

0.16

atically

0.16

iosis

0.15

umber

0.15

etat

0.15

eket

0.15

pering

0.14

antics

0.14

Activations Density 0.013%

various references to "schemes."

No Comments

No Known Activations