INDEX

Explanations

details related to personal and domestic items that evoke memories or symbolize significant aspects of life

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

ìĭľëĬĶ

-0.15

PyObject

-0.15

olk

-0.14

Éµ

-0.14

/Branch

-0.14

anko

-0.14

 Ø§Ø®

-0.13

 MERCHANTABILITY

-0.13

abilit

-0.13

UILDER

-0.13

POSITIVE LOGITS

 items

0.23

 Items

0.19

items

0.18

 materials

0.18

(items

0.16

-items

0.16

Items

0.16

.items

0.15

izers

0.15

íĴĪ

0.15

Activations Density 0.648%

details related to personal and domestic items that evoke memories or symbolize significant aspects of life

No Comments

No Known Activations