INDEX

Explanations

the frequency and context of personal pronouns in conversational text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ensch

-0.16

idan

-0.16

 migrationBuilder

-0.16

needed

-0.15

ta

-0.15

emoc

-0.14

 ADDR

-0.14

jmu

-0.14

aspers

-0.14

asal

-0.14

POSITIVE LOGITS

 already

0.21

 heard

0.20

already

0.17

 Heard

0.16

 know

0.16

heard

0.16

á»¥y

0.16

0.15

NOP

0.15

-flex

0.15

Activations Density 0.145%

the frequency and context of personal pronouns in conversational text

No Comments

No Known Activations