INDEX

Explanations

programming-related keywords and concepts, especially related to functions and variables

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

nga

-0.17

å¤ķ

-0.17

otten

-0.16

zung

-0.16

asca

-0.16

otto

-0.16

isse

-0.16

sov

-0.15

 lÃłng

-0.15

liner

-0.15

POSITIVE LOGITS

unik

0.16

cle

0.15

sil

0.15

 Technician

0.15

fdc

0.15

 folk

0.14

 Cure

0.14

Gaz

0.14

 Word

0.14

Activations Density 0.005%

programming-related keywords and concepts, especially related to functions and variables

No Comments

No Known Activations