INDEX

Explanations

relational phrases and inquiries about connections or meanings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

meer

-0.17

ABCDEFG

-0.16

uer

-0.15

linger

-0.14

 kÃ¸

-0.14

ÐºÐ°Ð½

-0.13

 Mayer

-0.13

ems

-0.13

TRIES

-0.13

lite

-0.13

POSITIVE LOGITS

'gc

0.15

ublic

0.13

athers

0.13

azine

0.13

empo

0.13

 ï»¿

0.13

dit

0.12

embr

0.12

gnore

0.12

âĢį

0.12

Activations Density 0.169%

relational phrases and inquiries about connections or meanings

No Comments

No Known Activations