INDEX

Explanations

phrases that express conditions, permissions, and requirements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

adu

-0.15

/GPL

-0.14

bone

-0.14

 snag

-0.14

ouz

-0.14

ovenant

-0.13

enny

-0.13

hei

-0.13

Ã«n

-0.13

ashi

-0.13

POSITIVE LOGITS

 contr

0.17

 Contr

0.15

inar

0.14

 CONTR

0.14

åĽ

0.14

orf

0.14

 kennenlernen

0.13

ãĥ¼ãĥĨ

0.13

 Mayer

0.13

ÑĦÑĤ

0.13

Activations Density 0.717%

phrases that express conditions, permissions, and requirements

No Comments

No Known Activations