INDEX

Explanations

references to file or package structures related to software projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ycz

-0.16

-0.15

allee

-0.15

orz

-0.15

-operator

-0.14

olin

-0.14

 proposals

-0.14

Ð¾Ð½

-0.13

alla

-0.13

POSITIVE LOGITS

ppers

0.16

util

0.15

.util

0.15

.misc

0.15

Ð¾Ð»Ð¾Ñģ

0.15

OutOfBoundsException

0.14

abinet

0.14

(DialogInterface

0.14

å¢

0.14

 queryInterface

0.14

Activations Density 0.010%

references to file or package structures related to software projects

No Comments

No Known Activations