INDEX

Explanations

queries and expressions of uncertainty related to choices and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

odable

-0.16

 èĩ

-0.16

anth

-0.16

ÑģÐºÐ°

-0.16

edla

-0.15

swer

-0.14

ITTE

-0.14

otal

-0.14

ÑģÑĮÐºÐ¾

-0.14

.ArgumentParser

-0.13

POSITIVE LOGITS

0.15

Sik

0.14

DataManager

0.14

brig

0.14

Ay

0.14

Ñī

0.14

 cooperating

0.13

ìļ´ëį°

0.13

 Olymp

0.13

Activations Density 0.089%

queries and expressions of uncertainty related to choices and assessments

No Comments

No Known Activations