INDEX

Explanations

references to ticketing or access-related phrases in a context involving events or attractions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Canton

-0.15

PointSize

-0.14

kova

-0.13

uraa

-0.13

vern

-0.13

ë°Ģ

-0.13

.navigator

-0.13

nika

-0.13

.scalablytyped

-0.13

arena

-0.13

POSITIVE LOGITS

iken

0.15

pack

0.15

OLUM

0.14

olith

0.14

NG

0.14

Ð¾Ð¹Ð½Ð¾

0.14

ikt

0.14

otty

0.13

NG

0.13

leep

0.13

Activations Density 0.154%

references to ticketing or access-related phrases in a context involving events or attractions

No Comments

No Known Activations