INDEX

Explanations

terms related to graph theory and causal relationships

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

raj

-0.18

irut

-0.15

ahn

-0.15

amac

-0.15

	Copyright

-0.15

datatable

-0.15

amaz

-0.14

Ø§ÙĦÙĥ

-0.14

arf

-0.14

âĶĤ

-0.14

POSITIVE LOGITS

-add

0.16

azzi

0.16

add

0.16

anta

0.15

=add

0.15

DialogTitle

0.15

ADD

0.15

ãĥ¼ãĥ«

0.15

apur

0.14

åłĤ

0.14

Activations Density 0.152%

terms related to graph theory and causal relationships

No Comments

No Known Activations

terms related to graph theory and causal relationships

No Comments

No Known Activations