INDEX

Explanations

references to stages or evaluations in a process, particularly in a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

orno

-0.16

aly

-0.16

imer

-0.15

Ð¾Ð»Ð¾Ð´

-0.15

 Reduction

-0.15

Â¯ÃĤ

-0.14

_unused

-0.14

achs

-0.14

rikes

-0.14

rike

-0.14

POSITIVE LOGITS

 weekends

0.29

 Weekend

0.20

 weekend

0.18

 source

0.17

ROL

0.15

 sourceMappingURL

0.15

 grass

0.14

 short

0.14

 present

0.14

 seni

0.14

Activations Density 0.078%

references to stages or evaluations in a process, particularly in a formal context

No Comments

No Known Activations