INDEX

Explanations

references to the name "Katie" or similar variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iro

-0.17

aws

-0.17

ts

-0.15

rett

-0.15

rams

-0.15

ç·Ĵ

-0.15

unu

-0.15

labs

-0.14

haven

-0.14

 Popular

-0.14

POSITIVE LOGITS

 Perry

0.16

ungan

0.16

did

0.15

ÐµÐ³Ð¾Ð´Ð½Ñı

0.15

meni

0.14

 COUR

0.14

ISTIC

0.14

 Cour

0.14

 McCabe

0.14

ToUpper

0.14

Activations Density 0.009%

references to the name "Katie" or similar variations

No Comments

No Known Activations