INDEX

Explanations

references to editing and writing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

UnderTest

-0.16

zby

-0.14

erval

-0.14

podob

-0.14

Comparator

-0.14

 Desert

-0.14

lanma

-0.14

MOVED

-0.14

 unus

-0.13

appa

-0.13

POSITIVE LOGITS

emb

0.16

embre

0.15

 final

0.15

ancode

0.14

_cpp

0.14

 kuru

0.14

AZE

0.14

fic

0.14

emb

0.14

odb

0.14

Activations Density 0.131%

references to editing and writing processes

No Comments

No Known Activations