INDEX

Explanations

occurrences of numerical information related to publications and their distribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ssi

-0.15

ousel

-0.14

upro

-0.14

 Pract

-0.14

Ð¿ÐµÑĩ

-0.14

Dow

-0.14

 Stein

-0.14

Ä©nh

-0.14

contres

-0.13

oscope

-0.13

POSITIVE LOGITS

iei

0.17

Ð²Ð°ÑĤ

0.16

 copies

0.15

vez

0.15

dak

0.15

ë³¸

0.14

Distribution

0.14

 batches

0.14

hazi

0.14

 production

0.14

Activations Density 0.274%

occurrences of numerical information related to publications and their distribution

No Comments

No Known Activations

occurrences of numerical information related to publications and their distribution

No Comments

No Known Activations