INDEX

Explanations

timestamp information in the text

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

notated

-0.16

wide

-0.15

emen

-0.14

annot

-0.14

bane

-0.14

hus

-0.14

Ä

-0.14

nen

-0.14

 nameof

-0.14

 MetroFramework

-0.14

POSITIVE LOGITS

PM

0.38

pm

0.37

PM

0.33

pm

0.33

_pm

0.28

_PM

0.28

pm

0.23

(pm

0.22

am

0.20

 ìĺ¤íĽĦ

0.18

Activations Density 0.009%

timestamp information in the text

No Comments

No Known Activations