INDEX

Explanations

numerical representations and patterns related to statistics or probabilities

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

bug

-0.16

 Playground

-0.15

endas

-0.14

hurst

-0.14

Pip

-0.14

iza

-0.14

 Force

-0.14

bug

-0.14

 Ending

-0.14

beros

-0.14

POSITIVE LOGITS

 thousand

0.18

 hundred

0.17

amework

0.16

.dsl

0.15

undred

0.15

ãĥ¬ãĥ¼

0.15

 à¤¹à¤ľ

0.14

 thousands

0.14

¡°

0.14

 YÃ¼z

0.14

Activations Density 0.041%

numerical representations and patterns related to statistics or probabilities

No Comments

No Known Activations