INDEX

Explanations

references to interviews and the context surrounding them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ovit

-0.16

owing

-0.16

heim

-0.15

erland

-0.15

izons

-0.15

readcr

-0.15

á»©t

-0.15

ÑĳÐ¼

-0.15

ade

-0.15

osal

-0.15

POSITIVE LOGITS

ees

0.21

ys

0.17

ee

0.17

ulse

0.15

rech

0.15

avoid

0.15

 spoken

0.14

ined

0.14

lsa

0.14

Activations Density 0.018%

references to interviews and the context surrounding them

No Comments

No Known Activations