INDEX

Explanations

references to assistance or support systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lak

-0.16

inx

-0.16

ucci

-0.15

 Chern

-0.14

orio

-0.14

furt

-0.14

 Exit

-0.14

 Hearth

-0.14

 çķ

-0.14

oli

-0.13

POSITIVE LOGITS

plate

0.17

ÐµÑĢÐ¸Ð½

0.17

zer

0.16

ijn

0.15

lej

0.15

anyl

0.15

ByUrl

0.15

 nutshell

0.15

0.14

asion

0.14

Activations Density 0.864%

references to assistance or support systems

No Comments

No Known Activations