INDEX

Explanations

statements and assertions made by individuals, particularly in a medical or research context

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

imas

-0.15

Ì§

-0.15

uelle

-0.15

ãģĭãģ£ãģ¦

-0.15

Ĳ

-0.15

ÙĪÚ©

-0.15

Ð¾Ð»Ð¸ÑĤ

-0.14

ÑĢÐ°Ð·Ñĥ

-0.14

anton

-0.14

POSITIVE LOGITS

bjerg

0.16

bred

0.15

odic

0.15

 term

0.15

irsch

0.14

/gtest

0.14

ãģĹãģı

0.14

Ð»Ð¸Ð²

0.14

(FILE

0.13

xa

0.13

Activations Density 0.017%

statements and assertions made by individuals, particularly in a medical or research context

No Comments

No Known Activations