INDEX

Explanations

instances of the word "program" along with various expressions of "real" or related sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

feld

-0.15

ÑĩÐ°ÑĤ

-0.15

erece

-0.14

rence

-0.14

}());↵

-0.14

ChartData

-0.14

à¥ģà¤¶

-0.14

çİĦ

-0.14

getti

-0.14

 batt

-0.14

POSITIVE LOGITS

(:

0.17

 intent

0.17

 subroutine

0.16

ìĿ´ìĸ´

0.16

logical

0.16

ynn

0.16

 Fort

0.16

 Jacqu

0.15

 &↵

0.15

intent

0.15

Activations Density 0.016%

instances of the word "program" along with various expressions of "real" or related sentiments

No Comments

No Known Activations