INDEX

Explanations

elements related to noteworthy achievements and unique experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

iband

-0.15

 Claw

-0.15

choice

-0.14

Lyn

-0.14

rch

-0.14

 Eudicots

-0.14

Ð¾ÑĢÐ°Ñı

-0.14

idual

-0.14

cta

-0.13

ê·ł

-0.13

POSITIVE LOGITS

 probably

0.22

 perhaps

0.19

çļĦæĺ¯

0.18

 Probably

0.18

probably

0.17

 apart

0.17

èİ«

0.17

ãģ®ãģ¯

0.16

Probably

0.16

ÑıÑĩ

0.16

Activations Density 0.139%

elements related to noteworthy achievements and unique experiences

No Comments

No Known Activations