INDEX

Explanations

references to "Our" or possessive pronouns indicating belonging or connection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ãĥ³ãĥĹ

-0.15

vell

-0.15

ãĥ¥ãĥ¼

-0.15

elly

-0.15

antes

-0.15

annt

-0.14

ampler

-0.14

/device

-0.14

antas

-0.14

POSITIVE LOGITS

 Light

0.18

Lite

0.17

 light

0.17

_light

0.17

Ã¡t

0.15

Light

0.15

 lights

0.15

éħ

0.15

LIGHT

0.15

åĲ

0.15

Activations Density 0.047%

references to "Our" or possessive pronouns indicating belonging or connection

No Comments

No Known Activations