INDEX

Explanations

mentions of meetings, programs, and events in a professional or organizational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ndef

-0.14

ptal

-0.13

bre

-0.13

tainment

-0.13

oust

-0.13

sonian

-0.13

iÅŁleri

-0.13

azo

-0.13

czy

-0.13

 *);↵↵

-0.13

POSITIVE LOGITS

 Encounter

0.17

è¿ĩåİ»

0.17

adil

0.16

orpor

0.14

 specials

0.14

 INCIDENT

0.14

 perfil

0.13

 handy

0.13

ÑĤÑĢÐ¾Ð½

0.13

(pdf

0.13

Activations Density 0.001%

mentions of meetings, programs, and events in a professional or organizational context

No Comments

No Known Activations