INDEX

Explanations

ingredients and components used in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

olet

-0.17

vester

-0.16

à¸²à¸ģ

-0.15

agini

-0.14

pz

-0.14

 Sender

-0.14

\Modules

-0.13

HZ

-0.13

asctime

-0.13

POSITIVE LOGITS

eco

0.15

egen

0.14

_HANDLE

0.14

 Narrow

0.13

 bureaucratic

0.13

 prow

0.13

 Transitional

0.13

mus

0.13

 bureaucr

0.13

Mu

0.13

Activations Density 0.070%

ingredients and components used in recipes

No Comments

No Known Activations