INDEX

Explanations

terms related to medical and scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Serialized

-0.17

nees

-0.15

icky

-0.14

nav

-0.14

 Starr

-0.14

baugh

-0.14

otal

-0.14

DataContract

-0.13

-flat

-0.13

inary

-0.13

POSITIVE LOGITS

onte

0.16

_PHP

0.15

jun

0.14

"@

0.14

stime

0.14

ept

0.14

stown

0.14

.AppendFormat

0.13

||↵

0.13

ãĤ¨ãĥ«

0.13

Activations Density 0.005%

terms related to medical and scientific research

No Comments

No Known Activations