INDEX

Explanations

expressions of uncertainty and questions related to knowledge or understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

/apt

-0.16

anko

-0.16

ERCHANT

-0.16

anki

-0.16

iele

-0.15

hower

-0.15

izza

-0.15

asher

-0.15

ashion

-0.14

hin

-0.14

POSITIVE LOGITS

asaki

0.17

elter

0.15

ampa

0.14

lt

0.14

 Acid

0.14

ckt

0.14

,[],

0.14

vre

0.14

Exposed

0.14

vi

0.13

Activations Density 0.062%

expressions of uncertainty and questions related to knowledge or understanding

No Comments

No Known Activations

expressions of uncertainty and questions related to knowledge or understanding

No Comments

No Known Activations