INDEX

Explanations

uses of the word "that" 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 here

-0.16

here

-0.15

rub

-0.15

emma

-0.15

no

-0.15

 process

-0.15

upp

-0.15

iard

-0.14

now

-0.14

 processes

-0.14

POSITIVE LOGITS

SENS

0.17

ssc

0.16

engu

0.16

letic

0.16

egrator

0.16

abo

0.16

ables

0.16

ovah

0.15

Ã¶ÄŁ

0.15

unkt

0.15

Activations Density 0.100%

uses of the word "that" in various contexts

No Comments

No Known Activations