INDEX

Explanations

terms related to hospitalization and medical treatment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iminal

-0.16

ember

-0.15

åİ

-0.14

 chars

-0.14

 char

-0.14

ifying

-0.14

-char

-0.14

 saja

-0.13

rita

-0.13

POSITIVE LOGITS

oley

0.15

hog

0.14

ilt

0.14

ND

0.14

Å¡ek

0.14

 Starter

0.14

oba

0.13

ice

0.13

urt

0.13

Cover

0.13

Activations Density 0.006%

terms related to hospitalization and medical treatment

No Comments

No Known Activations