INDEX

Explanations

specific letter patterns or sequences within words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

aceous

-0.17

ream

-0.17

peater

-0.16

ARGIN

-0.15

irsch

-0.15

oud

-0.15

placer

-0.15

EDIUM

-0.14

ãģįãģŁ

-0.14

occan

-0.14

POSITIVE LOGITS

0.20

-vous

0.20

illow

0.19

illions

0.18

ephy

0.18

ephir

0.18

abbix

0.18

zy

0.18

ãĤ©

0.17

(es

0.17

Activations Density 0.378%

specific letter patterns or sequences within words

No Comments

No Known Activations