INDEX

Explanations

references to objects and their properties in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

omik

-0.14

omite

-0.13

ovo

-0.13

ueil

-0.13

arget

-0.13

oble

-0.13

ãĥ¼ãĥ«

-0.13

lier

-0.13

tu

-0.13

POSITIVE LOGITS

ISTR

0.16

isser

0.15

ystery

0.14

ucchini

0.14

apon

0.14

åľ³

0.14

ogg

0.14

abor

0.14

TEGR

0.13

 Horton

0.13

Activations Density 0.082%

references to objects and their properties in programming contexts

No Comments

No Known Activations