INDEX

Explanations

phrases that express the idea of non-existence or absolute conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

lix

-0.15

 Pride

-0.14

arten

-0.14

xdb

-0.14

tracker

-0.14

awa

-0.14

 challenge

-0.14

kich

-0.14

 diam

-0.13

RTC

-0.13

POSITIVE LOGITS

agged

0.16

Fry

0.14

ound

0.14

Ä±rak

0.13

ahl

0.13

haf

0.13

iem

0.13

ChildIndex

0.13

rosso

0.13

Activations Density 0.070%

phrases that express the idea of non-existence or absolute conditions

No Comments

No Known Activations