INDEX

Explanations

programming terms and functions related to object-oriented programming and mathematical notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

»

-0.16

_completion

-0.15

[".

-0.15

anko

-0.14

.jackson

-0.14

igham

-0.14

acci

-0.14

 undert

-0.14

<Q

-0.14

POSITIVE LOGITS

reesome

0.15

Ð¾Ñİ

0.15

 Siege

0.14

 Nicholson

0.14

ieder

0.14

 itself

0.14

VIEW

0.14

 èı

0.14

geber

0.14

anos

0.14

Activations Density 0.146%

programming terms and functions related to object-oriented programming and mathematical notations

No Comments

No Known Activations