INDEX

Explanations

information related to statistical data and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Taiwanese

-0.16

otel

-0.15

stanbul

-0.15

_MSK

-0.14

oksen

-0.14

 conce

-0.14

Ãªu

-0.14

clair

-0.14

coc

-0.14

POSITIVE LOGITS

 çĶ³åįļ

0.15

bil

0.15

-X

0.15

.X

0.15

bine

0.15

 Ð¿Ð°Ð»

0.15

 Nacht

0.14

mares

0.14

*X

0.14

Activations Density 0.038%

information related to statistical data and reports

No Comments

No Known Activations

information related to statistical data and reports

No Comments

No Known Activations