INDEX

Explanations

references to specific measurement biases or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

DNA

-0.15

DNA

-0.15

 meds

-0.14

ÏģÎ¹Î¬

-0.14

ekim

-0.14

 theater

-0.14

 genomes

-0.13

 genetics

-0.13

alette

-0.13

 demographics

-0.13

POSITIVE LOGITS

 poet

0.25

 poem

0.23

 stanza

0.21

 narrator

0.19

0.18

 poems

0.17

 poets

0.16

'(

0.16

'\

0.16

‘

0.15

Activations Density 0.005%

references to specific measurement biases or characteristics

No Comments

No Known Activations