INDEX

Explanations

connections and relationships between various elements in a complex context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

efs

-0.16

adera

-0.15

 evacuated

-0.14

å°ıåŃ¦

-0.14

.ipv

-0.14

åħį

-0.14

 discharged

-0.14

 Categoria

-0.13

 Hlav

-0.13

iner

-0.13

POSITIVE LOGITS

habi

0.16

ecast

0.15

Ã¨n

0.14

iffer

0.14

 Ø®Ø§Ú©

0.14

Î³Ïĩ

0.14

æ£

0.14

æŁĶ

0.14

_finalize

0.14

Activations Density 0.531%

connections and relationships between various elements in a complex context

No Comments

No Known Activations