INDEX

Explanations

phrases indicating an increase in quantity or availability

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

alars

-0.16

ï»¿#

-0.16

amer

-0.15

ulumi

-0.15

piler

-0.15

senal

-0.15

nants

-0.15

tual

-0.15

-tm

-0.14

¶Į

-0.14

POSITIVE LOGITS

à¤·

0.18

 Patri

0.16

oe

0.15

-than

0.15

 than

0.15

 Till

0.14

Uri

0.14

Browse

0.14

OT

0.14

 Break

0.14

Activations Density 0.015%

phrases indicating an increase in quantity or availability

No Comments

No Known Activations