INDEX

Explanations

references to legal documents and structured information, such as tables and columns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Liberties

-0.17

Ã´i

-0.16

rett

-0.16

arity

-0.16

ipp

-0.15

[sizeof

-0.15

abbit

-0.15

orias

-0.14

arak

-0.14

onga

-0.14

POSITIVE LOGITS

 Schedule

0.17

ba

0.16

za

0.15

zenie

0.15

Schedule

0.15

insert

0.14

 references

0.14

Ð½Ð¾ÑģÐ¸

0.14

ZA

0.14

Ba

0.14

Activations Density 0.003%

references to legal documents and structured information, such as tables and columns

No Comments

No Known Activations