INDEX

Explanations

phrases indicating repetition or nostalgia

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

isÃŃ

-0.17

ãĥķãĤ§

-0.17

urum

-0.16

erring

-0.15

ondon

-0.14

 Marvin

-0.14

erland

-0.14

enticator

-0.14

ozor

-0.14

oksen

-0.14

POSITIVE LOGITS

 again

0.32

again

0.26

 Again

0.24

 repeat

0.23

Again

0.23

 Ð¿Ð¾Ð²ÑĤÐ¾ÑĢ

0.21

 Repeat

0.21

 novamente

0.21

 láº¡i

0.20

AGAIN

0.20

Activations Density 0.204%

phrases indicating repetition or nostalgia

No Comments

No Known Activations