INDEX

Explanations

descriptive phrases about geographic positioning and boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

æķ·

-0.17

enet

-0.16

strup

-0.16

ÏĥÏĦÎ®

-0.15

uddy

-0.15

ç«

-0.15

-transfer

-0.15

 Uncomment

-0.14

ÏįÎ½

-0.14

ãģªãģĮãĤī

-0.14

POSITIVE LOGITS

 sides

0.26

 surround

0.25

 surrounds

0.22

 surrounding

0.18

 surrounded

0.18

walls

0.17

 walls

0.17

 sided

0.17

(side

0.17

_ctxt

0.16

Activations Density 0.080%

descriptive phrases about geographic positioning and boundaries

No Comments

No Known Activations