INDEX

Explanations

references to various types of shops and bookstores

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

owa

-0.15

ICODE

-0.15

.addObserver

-0.14

OrElse

-0.14

adal

-0.14

 Binder

-0.14

ssi

-0.14

à¸±à¸Ĺ

-0.14

ajs

-0.14

POSITIVE LOGITS

etti

0.18

NaN

0.17

ÏĦÏī

0.16

Ð¿Ð¾ÑĢ

0.14

hammer

0.14

olet

0.14

peaker

0.14

ropolis

0.13

@index

0.13

 surfaces

0.13

Activations Density 0.023%

references to various types of shops and bookstores

No Comments

No Known Activations