INDEX

Explanations

repeated patterns or references to "loop" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ibs

-0.18

ebo

-0.18

quez

-0.16

onne

-0.15

lee

-0.15

onse

-0.15

.uf

-0.15

wig

-0.14

Cru

-0.14

../

-0.14

POSITIVE LOGITS

-loop

0.27

(loop

0.21

 loop

0.21

 Loop

0.20

Loop

0.19

loop

0.19

 LOOP

0.18

 loops

0.17

.loop

0.17

otron

0.16

Activations Density 0.016%

repeated patterns or references to "loop" in various contexts

No Comments

No Known Activations