INDEX

Explanations

expressions related to belief or confidence in something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

dea

-0.17

nie

-0.16

yh

-0.16

ĭ

-0.15

utz

-0.15

IENTATION

-0.15

quel

-0.14

/devices

-0.14

æ¡Ĥ

-0.14

ses

-0.14

POSITIVE LOGITS

ance

0.22

ably

0.18

lessly

0.17

worthy

0.16

 strongly

0.16

vably

0.16

vers

0.16

fulness

0.16

ÅĽmy

0.15

fully

0.15

Activations Density 0.040%

expressions related to belief or confidence in something

No Comments

No Known Activations