INDEX

Explanations

elements related to film production and edits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

arsi

-0.16

 slightly

-0.15

 somewhat

-0.15

 sometimes

-0.14

ãģıãĤĮ

-0.14

 æ³

-0.14

 Eventually

-0.14

 ÑĤÐ¾Ð¶Ðµ

-0.13

AppComponent

-0.13

Ã¶t

-0.13

POSITIVE LOGITS

 absolutely

0.25

 Absolutely

0.21

 ráº¥t

0.20

far

0.19

 very

0.19

Absolutely

0.19

 entirely

0.19

far

0.19

 quite

0.19

 anything

0.18

Activations Density 0.056%

elements related to film production and edits

No Comments

No Known Activations