INDEX

Explanations

questions and inquiry phrases related to understanding and evaluating information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Sort

-0.19

Sort

-0.18

 Solve

-0.17

Convert

-0.16

Get

-0.15

_Execute

-0.14

Collect

-0.14

Expand

-0.14

Compute

-0.13

Use

-0.13

POSITIVE LOGITS

 does

0.64

 Does

0.58

are

0.52

Are

0.51

how

0.50

did

0.49

Is

0.49

can

0.48

does

0.47

Does

0.47

Activations Density 1.342%

questions and inquiry phrases related to understanding and evaluating information

No Comments

No Known Activations