INDEX

Explanations

terms related to medical procedures and patient rights

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

ako

-0.15

Ree

-0.15

quee

-0.14

gon

-0.14

rips

-0.14

\<^

-0.14

 stool

-0.14

esModule

-0.14

ainer

-0.14

 Karn

-0.14

POSITIVE LOGITS

ÑĤÐ°Ñħ

0.17

elled

0.16

ales

0.15

 Howe

0.15

BUF

0.14

Äįel

0.14

Äįet

0.14

enser

0.14

ìĿ´ëĵľ

0.14

tai

0.14

Activations Density 0.019%

terms related to medical procedures and patient rights

No Comments

No Known Activations