INDEX

Explanations

terms related to responsibility and transparency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

lingen

-0.15

aat

-0.15

ongan

-0.15

veau

-0.14

.Encoding

-0.14

ikt

-0.14

oin

-0.14

Unlock

-0.14

ilo

-0.14

è¨Ģèĳī

-0.14

POSITIVE LOGITS

tom

0.15

afil

0.14

ADE

0.13

chia

0.13

respons

0.13

iez

0.13

atest

0.13

utions

0.13

arse

0.13

 Gang

0.13

Activations Density 0.008%

terms related to responsibility and transparency in various contexts

No Comments

No Known Activations