INDEX

Explanations

occurrences of the pronoun "it" and variations in its 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

kers

-0.15

ersen

-0.14

 æĽ

-0.14

ÙĨØ´

-0.14

undry

-0.14

dit

-0.13

iny

-0.13

iatrics

-0.13

 depart

-0.13

usal

-0.13

POSITIVE LOGITS

 soon

0.25

 weren

0.25

 wasn

0.24

soon

0.23

 quickly

0.19

 therefore

0.19

 shouldn

0.19

Soon

0.19

 Soon

0.18

quick

0.18

Activations Density 0.098%

occurrences of the pronoun "it" and variations in its usage

No Comments

No Known Activations