INDEX

Explanations

occurrences of the word "there" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

nya

-0.22

 here

-0.20

there

-0.20

 ÑĤÐ°Ð¼

-0.19

ting

-0.19

shit

-0.19

iture

-0.18

sWith

-0.18

ned

-0.18

 ÑĤÑĥÑĤ

-0.18

POSITIVE LOGITS

abouts

0.48

upon

0.33

unto

0.30

on

0.28

fore

0.27

after

0.27

from

0.24

under

0.22

ina

0.22

aus

0.22

Activations Density 0.046%

occurrences of the word "there" in various contexts

No Comments

No Known Activations