INDEX

Explanations

discussions about prioritizing resources and societal issues

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

Ã¨ve

-0.16

isoft

-0.15

sville

-0.15

 bekl

-0.15

 NÄĽm

-0.15

 Soft

-0.14

illis

-0.14

anken

-0.14

mitt

-0.14

opper

-0.14

POSITIVE LOGITS

 instead

0.25

instead

0.24

 real

0.22

 focus

0.22

 Instead

0.22

Instead

0.21

 Focus

0.21

 priority

0.21

 elsewhere

0.20

focus

0.20

Activations Density 0.187%

discussions about prioritizing resources and societal issues

No Comments

No Known Activations