INDEX

Explanations

recurring themes of repetition and accountability in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ains

-0.17

AINS

-0.17

 bufsize

-0.15

kar

-0.14

atz

-0.13

iam

-0.13

oby

-0.13

Or

-0.13

 intens

-0.13

POSITIVE LOGITS

 again

0.22

 åıĪ

0.19

 another

0.19

ebi

0.19

 láº¡i

0.18

Again

0.18

another

0.17

 Again

0.17

åıĪ

0.17

tÃŃ

0.16

Activations Density 0.139%

recurring themes of repetition and accountability in various contexts

No Comments

No Known Activations