INDEX

Explanations

interactions and relationships between individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.cv

-0.16

buc

-0.15

NSE

-0.15

 offset

-0.15

Tul

-0.14

 èŃ

-0.14

gql

-0.14

ouz

-0.14

strup

-0.14

POSITIVE LOGITS

ippi

0.17

iger

0.16

 Digest

0.15

rement

0.14

ea

0.14

ybrid

0.14

\Catalog

0.14

ìĹĦ

0.14

AndWait

0.14

iento

0.13

Activations Density 0.260%

interactions and relationships between individuals

No Comments

No Known Activations