INDEX

Explanations

code related to attributes and properties in 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

èĪ

-0.19

 Hunt

-0.16

uta

-0.15

hunt

-0.14

rat

-0.14

emouth

-0.14

lei

-0.14

 Bhar

-0.14

-0.13

POSITIVE LOGITS

:eq

0.14

_lineno

0.14

prak

0.14

.fm

0.14

rier

0.14

ipse

0.14

.setHeader

0.14

amil

0.14

ERS

0.13

essaging

0.13

Activations Density 0.548%

code related to attributes and properties in a programming context

No Comments

No Known Activations