INDEX

Explanations

programming-related terms, specifically related to data models, file handling, and coding functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ouch

-0.15

elay

-0.14

uled

-0.14

phem

-0.14

riday

-0.14

imas

-0.14

omit

-0.13

èĦĤ

-0.13

 bitmask

-0.13

uye

-0.13

POSITIVE LOGITS

::=

0.15

Toolkit

0.13

dog

0.13

Dog

0.13

Dog

0.13

 ;č↵

0.13

Ð¸ÑģÑģ

0.13

.netbeans

0.12

 issue

0.12

 Schwar

0.12

Activations Density 0.712%

programming-related terms, specifically related to data models, file handling, and coding functions

No Comments

No Known Activations