INDEX

Explanations

programming-related syntax and commands

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

 Bren

-0.15

ple

-0.14

 Ment

-0.14

AMP

-0.14

eldon

-0.14

 accelerator

-0.14

zag

-0.14

Ã¡vÃ¡

-0.14

eres

-0.13

ÑĤÐ¾ÑĢ

-0.13

POSITIVE LOGITS

ardi

0.17

éı

0.15

 CharSet

0.14

nut

0.14

GestureRecognizer

0.14

yte

0.14

leck

0.14

ECH

0.14

luk

0.14

echo

0.13

Activations Density 0.074%

programming-related syntax and commands

No Comments

No Known Activations