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 @ 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

robat

-0.18

asso

-0.16

anzi

-0.15

Ð¾Ð»Ð¾

-0.14

achelor

-0.14

ension

-0.14

isz

-0.14

áº§y

-0.14

ersistent

-0.14

Ð±Ð°Ñģ

-0.14

POSITIVE LOGITS

mailto

0.15

 Agency

0.15

 Integral

0.15

0.14

-=

0.13

Ã¤ren

0.13

wagon

0.13

 Prim

0.13

Std

0.13

_yes

0.13

Activations Density 0.007%

references to family members and relationships

No Comments

No Known Activations