INDEX

Explanations

instances of numerical data and statistics related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rene

-0.17

anto

-0.16

inspace

-0.15

å¨

-0.14

acle

-0.14

onia

-0.14

YPES

-0.14

ows

-0.14

sku

-0.14

ia

-0.14

POSITIVE LOGITS

emodel

0.17

ovel

0.16

pii

0.15

Moh

0.15

nam

0.14

tainment

0.14

 pigment

0.14

äºī

0.14

avel

0.14

 large

0.14

Activations Density 0.110%

instances of numerical data and statistics related to various subjects

No Comments

No Known Activations