INDEX

Explanations

medical degrees and professional titles of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

qus

-0.16

ÄĻk

-0.15

SPATH

-0.15

ëĬ¥

-0.15

rne

-0.14

bson

-0.14

heck

-0.14

ikt

-0.14

opensource

-0.14

aby

-0.14

POSITIVE LOGITS

 FACE

0.19

MH

0.17

FAA

0.17

 habil

0.17

MBA

0.16

MPH

0.16

FA

0.15

Sc

0.15

 conce

0.15

 candidate

0.14

Activations Density 0.017%

medical degrees and professional titles of individuals

No Comments

No Known Activations