INDEX

Explanations

references to relationships and connections within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

'gc

-0.17

quo

-0.17

 âĹĦ

-0.15

äºĭåĭĻ

-0.15

rek

-0.14

rine

-0.14

Ð¼ÐµÑĢÐ¸Ðº

-0.14

 ((__

-0.14

unner

-0.14

ran

-0.14

POSITIVE LOGITS

 Ø¨Ø±Ø¬

0.15

 peri

0.15

ongyang

0.15

èĺ

0.14

 convey

0.14

izzo

0.14

ì²´

0.14

 vari

0.14

resa

0.14

Activations Density 0.373%

references to relationships and connections within various contexts

No Comments

No Known Activations