INDEX

Explanations

references to cities and urban areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

thur

-0.17

oken

-0.17

-caret

-0.16

¹Ħ

-0.15

RTL

-0.15

disposed

-0.15

imbus

-0.14

unma

-0.14

ountry

-0.14

.UnitTesting

-0.13

POSITIVE LOGITS

ajar

0.17

 core

0.15

core

0.15

ason

0.15

ICAST

0.15

 fathers

0.15

engo

0.15

erman

0.14

acher

0.14

zens

0.14

Activations Density 0.159%

references to cities and urban areas

No Comments

No Known Activations