INDEX

Explanations

terms related to medical conditions and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

adlo

-0.16

bek

-0.15

UIT

-0.15

.tie

-0.15

ech

-0.14

iri

-0.14

erd

-0.14

UIT

-0.14

 involvement

-0.14

ÐºÐ¾ÑĤ

-0.14

POSITIVE LOGITS

inkle

0.16

BOVE

0.15

theid

0.15

 mÃ¡t

0.14

izontal

0.14

ument

0.14

KANJI

0.14

uez

0.14

ignKey

0.14

endet

0.13

Activations Density 0.003%

terms related to medical conditions and processes

No Comments

No Known Activations