INDEX

Explanations

concepts related to identity and social variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

quist

-0.16

 Äįlov

-0.15

Amt

-0.15

 Henrik

-0.15

mbH

-0.15

arhus

-0.15

 Ã¥rhus

-0.14

 Ãĸn

-0.14

 pension

-0.14

Ã¤nge

-0.14

POSITIVE LOGITS

 term

0.19

 struk

0.17

met

0.16

jon

0.16

icit

0.15

 metab

0.15

 metabol

0.15

Äįin

0.15

 objekt

0.15

 metav

0.14

Activations Density 0.018%

concepts related to identity and social variables

No Comments

No Known Activations