INDEX

Explanations

references to regulatory documents and legal provisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abar

-0.18

etti

-0.18

mÃŃ

-0.14

lÃ¡n

-0.14

ARGER

-0.14

isma

-0.14

imap

-0.14

processable

-0.14

Ãºs

-0.13

POSITIVE LOGITS

Ep

0.16

Std

0.15

dsl

0.15

ep

0.15

tel

0.14

abin

0.13

-Sah

0.13

?>/

0.13

axon

0.13

 mono

0.13

Activations Density 0.145%

references to regulatory documents and legal provisions

No Comments

No Known Activations