INDEX

Explanations

references to a person's or organization's history of performance or success

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

auses

-0.16

 tracks

-0.16

TextStyle

-0.15

 trackers

-0.14

æŁ

-0.14

fa

-0.14

iske

-0.14

acock

-0.14

fern

-0.14

 Tracks

-0.14

POSITIVE LOGITS

 record

0.33

side

0.32

-record

0.31

record

0.29

listing

0.28

list

0.26

 Record

0.25

able

0.25

pad

0.25

down

0.24

Activations Density 0.019%

references to a person's or organization's history of performance or success

No Comments

No Known Activations