INDEX

Explanations

metrics and statistics related to averages and pricing

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

_defaults

-0.18

 averages

-0.17

å¹³åĿĩ

-0.17

obel

-0.17

.appspot

-0.16

 average

-0.15

 addCriterion

-0.15

 íıīê·ł

-0.14

jure

-0.14

 averaged

-0.14

POSITIVE LOGITS

 hoof

0.15

sof

0.15

arak

0.14

arat

0.14

athing

0.14

owler

0.14

 Across

0.13

dej

0.13

ont

0.13

OTO

0.13

Activations Density 0.050%

metrics and statistics related to averages and pricing

No Comments

No Known Activations