INDEX

Explanations

references to social interactions and group behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 mostly

-0.20

 vÄĽtÅ¡inou

-0.20

 Ð²ÑģÐµÑħ

-0.20

 generally

-0.19

 souvent

-0.19

 obvykle

-0.19

usually

-0.19

mostly

-0.18

ä½ķãģĭ

-0.18

 ëĮĢë¶Ģë¶Ħ

-0.18

POSITIVE LOGITS

 even

0.33

even

0.28

may

0.28

 sogar

0.26

çĶļèĩ³

0.26

 simply

0.23

Even

0.23

 Even

0.23

 outright

0.23

 dokonce

0.23

Activations Density 0.220%

references to social interactions and group behaviors

No Comments

No Known Activations