INDEX

Explanations

occurrences of the word "of" and its variants 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 @ 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

ãĤ¤ãĥ³ãĥĪ

-0.17

arra

-0.16

roup

-0.16

anken

-0.16

_animation

-0.16

 seri

-0.16

anker

-0.15

uchen

-0.15

Bindable

-0.15

 anim

-0.15

POSITIVE LOGITS

apa

0.15

 Chin

0.15

\Common

0.14

kul

0.14

ute

0.14

hit

0.14

nict

0.14

ope

0.14

 Preview

0.14

REST

0.14

Activations Density 0.019%

occurrences of the word "of" and its variants in various contexts

No Comments

No Known Activations