INDEX

Explanations

text related to social media or online engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ertainment

-0.14

agner

-0.14

avra

-0.13

-panel

-0.13

 âĢ¦↵↵

-0.13

 Fischer

-0.13

 panels

-0.13

_EOL

-0.13

APK

-0.13

lecture

-0.12

POSITIVE LOGITS

---

0.20

 ----

0.18

----

0.18

 Terr

0.18

 Municipal

0.17

-----

0.17

 owed

0.17

 -----

0.17

db

0.16

---

0.16

Activations Density 0.003%

text related to social media or online engagement

No Comments

No Known Activations