INDEX

Explanations

commented code or annotations within a programming context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inton

-0.15

thouse

-0.15

å

-0.14

opleft

-0.14

rud

-0.14

ahun

-0.14

.toObject

-0.14

ahat

-0.14

opic

-0.14

mscorlib

-0.13

POSITIVE LOGITS

piel

0.15

asaki

0.15

æĦŁ

0.14

Î¿Î»

0.13

paren

0.13

iÃ©n

0.13

pron

0.13

pulse

0.13

 GÃ¶z

0.13

Activations Density 0.031%

commented code or annotations within a programming context

No Comments

No Known Activations