INDEX

Explanations

references to templates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

anna

-0.15

tar

-0.15

Ð¾Ð´Ð¾

-0.15

ime

-0.14

na

-0.14

Ð¾Ð»ÐµÐ²Ð°

-0.14

fully

-0.14

nes

-0.14

ollo

-0.14

thumbnail

-0.14

POSITIVE LOGITS

/template

0.18

levision

0.16

yntax

0.16

ulse

0.15

ovÃŃ

0.15

sto

0.15

Æł

0.14

ULSE

0.14

chooser

0.14

.getOwnProperty

0.14

Activations Density 0.014%

references to templates

No Comments

No Known Activations