INDEX

Explanations

actions related to interaction and engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

èĥ½

-0.16

illon

-0.16

 MyBase

-0.15

.LayoutStyle

-0.15

.MockMvc

-0.14

 BaseService

-0.14

raham

-0.14

ORK

-0.13

yla

-0.13

CanBe

-0.13

POSITIVE LOGITS

ewise

0.15

ãģ¾ãģ¾

0.15

 anytime

0.15

ä¸Ģä¸ĭ

0.14

mpp

0.14

ttp

0.14

å¤ļå°ĳ

0.14

Ð¸ÑĤÐ¾Ð²

0.13

erin

0.13

unan

0.13

Activations Density 1.595%

actions related to interaction and engagement

No Comments

No Known Activations