INDEX

Explanations

connector words that indicate relationships or sequence in text

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

udas

-0.17

allee

-0.16

éģĵ

-0.15

akes

-0.14

ceph

-0.14

 mileage

-0.14

 Merrill

-0.14

åĨ

-0.14

 Witness

-0.14

 Perez

-0.14

POSITIVE LOGITS

fro

0.17

ogle

0.15

eco

0.15

ActionCreators

0.15

iesel

0.14

omu

0.14

_bw

0.14

calloc

0.14

enheim

0.14

emek

0.14

Activations Density 0.055%

connector words that indicate relationships or sequence in text

No Comments

No Known Activations