INDEX

Explanations

nested or hierarchical data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

utherford

-0.16

skin

-0.15

ÑĪÐµÐ¼

-0.14

azzo

-0.14

weise

-0.14

 punch

-0.14

arten

-0.13

aga

-0.13

enden

-0.13

ong

-0.13

POSITIVE LOGITS

 VÅ¡ech

0.16

ubber

0.16

 Salv

0.15

ÙĴÙĩ

0.15

Buzz

0.14

lobal

0.14

ERV

0.14

rette

0.14

ocha

0.14

cer

0.14

Activations Density 0.017%

nested or hierarchical data structures

No Comments

No Known Activations