INDEX

Explanations

phrases related to discussions, meetings, and agreements involving formal decisions

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

ovit

-0.15

ÑĥÑĩÐ°Ñģ

-0.15

iant

-0.14

ozem

-0.14

otte

-0.14

iÅ¾

-0.14

zo

-0.14

 press

-0.14

 linen

-0.13

rub

-0.13

POSITIVE LOGITS

ipa

0.15

 Tracker

0.15

.vaadin

0.14

hek

0.14

ackers

0.13

flush

0.13

avic

0.13

ory

0.13

ç¨

0.13

Activations Density 0.479%

phrases related to discussions, meetings, and agreements involving formal decisions

No Comments

No Known Activations