INDEX

Explanations

references to specific individuals or entities, particularly in cultural and geographical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rani

-0.20

nest

-0.15

WEEN

-0.15

 bark

-0.14

ichern

-0.14

bir

-0.14

 Banner

-0.13

 Ã©

-0.13

à¥°

-0.13

ekten

-0.13

POSITIVE LOGITS

pread

0.15

others

0.15

 anlay

0.15

ãĥ¥

0.15

ãģ£ãģ¨

0.14

Ð²ÐµÑģÑĤÐ¸

0.14

ØªÙĪØ§ÙĨ

0.14

Å¡e

0.14

ØªÙĨ

0.14

memberof

0.14

Activations Density 0.422%

references to specific individuals or entities, particularly in cultural and geographical contexts

No Comments

No Known Activations