INDEX

Explanations

specialized terms and phrases related to technical or administrative content, particularly in digital and software contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 ìĿ¸

-0.19

 incomes

-0.19

/interfaces

-0.19

 islands

-0.19

 ingredients

-0.19

 InputStream

-0.18

 investor

-0.18

 investors

-0.18

.inject

-0.18

-income

-0.17

POSITIVE LOGITS

II

0.18

II

0.17

,exports

0.17

 decrement

0.17

-export

0.17

 OutputStream

0.16

-II

0.16

aler

0.16

ALER

0.16

åĩºåı£

0.15

Activations Density 0.198%

specialized terms and phrases related to technical or administrative content, particularly in digital and software contexts

No Comments

No Known Activations