INDEX

Explanations

requests for information related to incidents or investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

anki

-0.15

aller

-0.15

-0.14

éķ

-0.14

 Conrad

-0.14

ANCED

-0.14

antal

-0.14

cheid

-0.14

ileo

-0.13

ERVE

-0.13

POSITIVE LOGITS

#Region

0.15

tf

0.14

rier

0.14

tual

0.14

ivicrm

0.14

 Barnes

0.13

bish

0.13

 association

0.13

AUSE

0.13

ague

0.13

Activations Density 0.013%

requests for information related to incidents or investigations

No Comments

No Known Activations