INDEX

Explanations

elements related to data manipulation and evaluation in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

alto

-0.14

 Angiospermae

-0.14

ify

-0.13

qrt

-0.13

ivre

-0.13

evin

-0.13

,self

-0.13

inqu

-0.13

arked

-0.13

AndGet

-0.12

POSITIVE LOGITS

;if

0.20

;↵

0.16

!;↵

0.13

ï¼Ľ↵

0.13

oka

0.13

{};↵

0.13

Ð¸ÑĤÐµÑĤ

0.13

=find

0.13

;č↵

0.13

Activations Density 0.265%

elements related to data manipulation and evaluation in programming

No Comments

No Known Activations