INDEX

Explanations

code structures and programming language syntax, particularly related to class and method definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

innacle

-0.16

ople

-0.14

OfType

-0.14

deque

-0.14

_dispatch

-0.14

itor

-0.14

atÄ±

-0.14

ê±°ëŀĺ

-0.13

ija

-0.13

SCO

-0.13

POSITIVE LOGITS

odore

0.16

gether

0.15

ÑĨÐµÐ¹

0.14

ournal

0.14

mlin

0.13

InParameter

0.13

æ®Ĭ

0.13

quarters

0.13

gli

0.13

Activations Density 0.162%

code structures and programming language syntax, particularly related to class and method definitions

No Comments

No Known Activations