INDEX

Explanations

mentions of notable locations and attractions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

eya

-0.18

erva

-0.16

crest

-0.15

ãĥĭãĥ¡

-0.15

.setSelection

-0.15

anny

-0.15

tery

-0.15

orge

-0.14

à¸§à¸Ķ

-0.14

adel

-0.14

POSITIVE LOGITS

abouts

0.18

0.16

 National

0.15

 admission

0.15

 Vict

0.15

 Admission

0.14

attr

0.14

ythe

0.14

aeper

0.14

Thr

0.14

Activations Density 0.559%

mentions of notable locations and attractions

No Comments

No Known Activations