INDEX

Explanations

words that refer to pronouns and their usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

liÅ¡

-0.15

 Secondary

-0.15

 Pyramid

-0.15

ter

-0.15

neys

-0.15

 doubly

-0.14

Pun

-0.14

 secondary

-0.14

ori

-0.14

 native

-0.14

POSITIVE LOGITS

 pron

0.31

 Pron

0.25

pron

0.23

 Singular

0.20

singular

0.18

azen

0.17

Us

0.17

 demonstr

0.17

Us

0.17

 singular

0.17

Activations Density 0.035%

words that refer to pronouns and their usage

No Comments

No Known Activations