INDEX

Explanations

descriptions of lightness and weight, as well as light-heartedness in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 ØªÙĤ

-0.14

èĴ

-0.14

atically

-0.14

Ã¤l

-0.14

cesso

-0.14

[src

-0.14

è¾

-0.14

ceph

-0.14

Ŀ

-0.13

iston

-0.13

POSITIVE LOGITS

ening

0.23

/light

0.23

ened

0.21

-duty

0.21

ning

0.20

weights

0.20

-weight

0.20

wei

0.19

-light

0.19

light

0.18

Activations Density 0.032%

descriptions of lightness and weight, as well as light-heartedness in context

No Comments

No Known Activations