INDEX

Explanations

coding-related keywords and phrases, particularly those relevant to task management and project updates

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

uhan

-0.17

 Speed

-0.14

oled

-0.14

loff

-0.14

enburg

-0.14

 cerv

-0.14

 kost

-0.13

jadi

-0.13

 speeds

-0.13

zza

-0.13

POSITIVE LOGITS

job

0.24

job

0.22

 jobs

0.20

-job

0.20

JOB

0.20

Job

0.19

.Job

0.18

/job

0.18

.job

0.18

è°ĥ

0.18

Activations Density 0.030%

coding-related keywords and phrases, particularly those relevant to task management and project updates

No Comments

No Known Activations