INDEX

Explanations

references to historical accounts and observations related to medicine and diseases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

//~

-0.15

_codegen

-0.14

recio

-0.14

 accordingly

-0.14

 agon

-0.14

uib

-0.14

ghan

-0.14

apolis

-0.14

 explo

-0.14

utenberg

-0.13

POSITIVE LOGITS

isle

0.18

leet

0.18

 Applications

0.16

iss

0.14

isme

0.14

Ì

0.14

_RM

0.14

ãĥ¼ãĤ¹ãĥĪ

0.14

intree

0.14

 applications

0.13

Activations Density 0.036%

references to historical accounts and observations related to medicine and diseases

No Comments

No Known Activations