INDEX

Explanations

code-related terms and concepts, particularly those involving programming logic, data handling, and document manipulation

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

ichel

-0.19

 Mell

-0.18

uml

-0.14

 Hollow

-0.14

ronym

-0.14

illery

-0.14

_VISIBLE

-0.14

 Verd

-0.14

 Gather

-0.14

 Lakes

-0.14

POSITIVE LOGITS

ÐºÑĢÐµÑĤ

0.15

 ÐļÐ¾ÑģÑĤ

0.15

achuset

0.14

ogl

0.14

Ð°Ð»Ð¾Ð³

0.14

kening

0.13

atk

0.13

.crt

0.13

positor

0.12

Activations Density 0.062%

code-related terms and concepts, particularly those involving programming logic, data handling, and document manipulation

No Comments

No Known Activations