INDEX

Explanations

terms related to medical or clinical guidelines and protocols

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 free

-0.16

bab

-0.15

getBytes

-0.15

ograms

-0.15

ICS

-0.15

Ã¼z

-0.15

illis

-0.14

acob

-0.14

ordin

-0.14

burgh

-0.14

POSITIVE LOGITS

 ÑģÐ»

0.15

ÑĤÐ¸Ð¼

0.14

 Twice

0.14

 á»ĳng

0.14

nier

0.14

 Bender

0.14

ersh

0.13

zx

0.13

oil

0.13

Activations Density 0.031%

terms related to medical or clinical guidelines and protocols

No Comments

No Known Activations