INDEX

Explanations

terms related to health care

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

oto

-0.19

gang

-0.18

ses

-0.17

areth

-0.16

sss

-0.16

saldo

-0.15

oms

-0.15

arel

-0.14

ertime

-0.14

borg

-0.14

POSITIVE LOGITS

legg

0.18

idla

0.16

dac

0.15

ThreadId

0.15

 ########.

0.15

vez

0.14

ffee

0.14

ordan

0.14

avity

0.14

lemn

0.13

Activations Density 0.012%

terms related to health care

No Comments

No Known Activations