INDEX

Explanations

identifiers or codes, particularly those that may be linked to authors or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

empo

-0.16

vise

-0.15

ycop

-0.15

ç«

-0.15

ecome

-0.15

åĨ

-0.15

IMAL

-0.15

esel

-0.14

 Ansi

-0.14

Ð³Ð¾Ð´

-0.14

POSITIVE LOGITS

OR

0.18

elsif

0.16

ouver

0.16

Orc

0.16

idget

0.15

orial

0.15

idge

0.15

 Schiff

0.14

OR

0.14

Mah

0.14

Activations Density 0.005%

identifiers or codes, particularly those that may be linked to authors or studies

No Comments

No Known Activations