INDEX

Explanations

questions and references to actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

isy

-0.16

longleftrightarrow

-0.16

byss

-0.16

_VF

-0.16

 Fucked

-0.16

 Heal

-0.15

 Mond

-0.15

onen

-0.15

[Unit

-0.15

à¥įà¤°à¤µ

-0.15

POSITIVE LOGITS

UMB

0.16

ana

0.16

kul

0.14

atives

0.14

agher

0.14

Ã¤t

0.13

kat

0.13

ulse

0.13

anou

0.13

å¸½

0.13

Activations Density 0.001%

questions and references to actions or processes

No Comments

No Known Activations