INDEX

Explanations

words related to health conditions and medical assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

åĶ¯

-0.19

-0.15

iven

-0.15

oker

-0.14

itter

-0.14

 Laud

-0.14

atatype

-0.14

DRAW

-0.14

ģm

-0.14

POSITIVE LOGITS

azo

0.17

_FAR

0.15

Å¾i

0.15

ophilia

0.14

pek

0.14

ãĥĥãĥĦ

0.14

icont

0.14

 Peak

0.14

edException

0.14

utomation

0.14

Activations Density 0.042%

words related to health conditions and medical assessments

No Comments

No Known Activations