INDEX

Explanations

terms related to enumeration and enumerated types 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

atcher

-0.17

guns

-0.15

pite

-0.14

rippling

-0.14

oppable

-0.14

.deb

-0.14

ç±

-0.14

CancelButton

-0.14

ÑĩÐ°Ñģ

-0.14

 Guaranteed

-0.14

POSITIVE LOGITS

iel

0.17

.scalablytyped

0.16

elda

0.16

heimer

0.15

ìĹ´

0.15

ãĥ¼ãĤ¹

0.15

BD

0.15

èŃ·

0.14

IMP

0.14

 Tobias

0.14

Activations Density 0.008%

terms related to enumeration and enumerated types in programming

No Comments

No Known Activations