INDEX

Explanations

references to new developments, applications, or policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

HeaderValue

-0.17

anker

-0.16

á»ģ

-0.15

berger

-0.15

idor

-0.15

oÅ¡

-0.14

 Angiospermae

-0.14

eldon

-0.14

urum

-0.14

acey

-0.13

POSITIVE LOGITS

new

0.19

 Ð½Ð¾Ð²ÑĭÐµ

0.17

(new

0.16

[new

0.15

-new

0.15

 nuevas

0.14

/new

0.14

new

0.14

ishi

0.14

new

0.14

Activations Density 0.099%

references to new developments, applications, or policies

No Comments

No Known Activations