INDEX

Explanations

medical terminology and research-related phrases

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

.inject

-0.15

 ghost

-0.14

%B

-0.14

adders

-0.13

Paren

-0.13

 Ghost

-0.13

oring

-0.13

unittest

-0.13

 ister

-0.13

.Global

-0.13

POSITIVE LOGITS

itten

0.16

ÑĤÑı

0.16

usty

0.15

 cases

0.15

ustum

0.15

oje

0.14

 experiences

0.14

 ë§Įì¡±

0.14

ritt

0.14

RICT

0.14

Activations Density 0.022%

medical terminology and research-related phrases

No Comments

No Known Activations