INDEX

Explanations

references to specific individuals or roles within a community context

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

my

-0.18

 tens

-0.17

OrNull

-0.15

 dozens

-0.15

 saya

-0.15

 even

-0.14

zens

-0.13

ebe

-0.13

&m

-0.13

decade

-0.13

POSITIVE LOGITS

çļĦéĹ®é¢ĺ

0.17

 Ekon

0.15

Ð»Ð°Ð³Ð°

0.15

çĽĽ

0.15

gio

0.15

agal

0.15

idl

0.14

oke

0.14

oÄŁ

0.14

surf

0.14

Activations Density 0.006%

references to specific individuals or roles within a community context

No Comments

No Known Activations