INDEX

Explanations

connections and relationships among subjects or themes

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

teri

-0.17

ÑĨÐ¸Ð¿

-0.15

boz

-0.14

ovol

-0.14

avr

-0.14

prov

-0.14

ellij

-0.13

ided

-0.13

ä¸ĵ

-0.13

_epi

-0.13

POSITIVE LOGITS

 related

0.26

related

0.21

 Related

0.21

 allied

0.20

-related

0.18

çĽ¸éĹľ

0.18

Related

0.18

 Allied

0.17

 pseudo

0.16

 RELATED

0.16

Activations Density 0.303%

connections and relationships among subjects or themes

No Comments

No Known Activations