INDEX

Explanations

references to academic publications and historical texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ã¹a

-0.16

insic

-0.14

orda

-0.14

Îµ

-0.14

outil

-0.14

<boost

-0.14

{})

-0.14

ourcing

-0.14

ording

-0.14

rowable

-0.13

POSITIVE LOGITS

 Anthem

0.14

0.13

ogan

0.13

ipo

0.13

Äįel

0.13

ipes

0.13

ØªÙĨ

0.13

 autop

0.13

 paging

0.13

loating

0.13

Activations Density 0.058%

references to academic publications and historical texts

No Comments

No Known Activations