INDEX

Explanations

references to family members and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

.memo

-0.16

rink

-0.15

qui

-0.14

 Lama

-0.14

Queryable

-0.14

ersonic

-0.14

Ã§o

-0.14

 Virgin

-0.14

blocking

-0.13

ãĥĨãĥ«

-0.13

POSITIVE LOGITS

ynn

0.20

dyn

0.19

aden

0.17

 Pais

0.16

 Dylan

0.16

onen

0.16

yn

0.15

uzey

0.15

 Cooper

0.15

Rig

0.15

Activations Density 0.088%

references to family members and relationships

No Comments

No Known Activations