INDEX

Explanations

words indicating quantities or counts related to groups or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

liv

-0.18

kus

-0.15

atori

-0.15

ãĥĭãĤ¢

-0.14

æħİ

-0.14

adier

-0.14

kus

-0.14

liv

-0.13

aph

-0.13

Liv

-0.13

POSITIVE LOGITS

 others

0.19

 other

0.19

 diÄŁer

0.18

other

0.17

its

0.16

ien

0.15

 anderen

0.15

 dalÅ¡ÃŃch

0.15

åħ¶ä»ĸ

0.15

 jego

0.15

Activations Density 0.142%

words indicating quantities or counts related to groups or categories

No Comments

No Known Activations