INDEX

Explanations

terms related to forensic and medical professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

lew

-0.17

 Provid

-0.16

 Guidelines

-0.15

 onBind

-0.15

uchen

-0.15

èĳ

-0.14

ERSION

-0.14

Äħd

-0.14

 Gors

-0.14

ãĤĨ

-0.14

POSITIVE LOGITS

 college

0.20

 packages

0.19

pc

0.18

 apply

0.17

 Packages

0.17

 train

0.17

 know

0.17

 fingers

0.17

 nice

0.16

 neighborhood

0.16

Activations Density 0.040%

terms related to forensic and medical professions

No Comments

No Known Activations