INDEX

Explanations

technical terms and processes related to evaluating and validating data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

caff

-0.17

OrNull

-0.14

ToDevice

-0.14

BuilderFactory

-0.14

ometrics

-0.13

Toy

-0.13

TEM

-0.13

sci

-0.13

 authoritative

-0.13

 bash

-0.13

POSITIVE LOGITS

.assertThat

0.19

 expectations

0.17

 memcmp

0.17

 expected

0.17

 Carp

0.15

roti

0.15

memcmp

0.14

iesel

0.14

Expected

0.14

 expectation

0.14

Activations Density 0.049%

technical terms and processes related to evaluating and validating data

No Comments

No Known Activations