INDEX

Explanations

phrases indicating causation or support for statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 that

-0.18

 THAT

-0.15

on

-0.15

rike

-0.15

omal

-0.14

 âĸĪâĸĪ

-0.14

 about

-0.14

 Ekon

-0.14

ropp

-0.14

 Loose

-0.14

POSITIVE LOGITS

eding

0.17

lis

0.16

zing

0.15

cluding

0.15

quired

0.15

ching

0.15

aning

0.15

 programm

0.15

mir

0.14

 staggering

0.14

Activations Density 0.257%

phrases indicating causation or support for statements

No Comments

No Known Activations