INDEX

Explanations

locations and geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.17

 Minute

-0.16

isse

-0.15

 Beste

-0.15

(preg

-0.15

akis

-0.14

 Unit

-0.14

Sto

-0.14

POSITIVE LOGITS

argar

0.20

lesh

0.19

esar

0.18

pal

0.17

igar

0.17

oli

0.17

maal

0.16

pur

0.16

odia

0.15

asthan

0.15

Activations Density 0.247%

locations and geographic references

No Comments

No Known Activations