INDEX

Explanations

phrases related to significant events or changes in policy and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ullan

-0.19

orce

-0.17

 sake

-0.17

ancock

-0.16

chemy

-0.14

equipment

-0.14

plementation

-0.13

omanip

-0.13

ecess

-0.13

POSITIVE LOGITS

}());↵

0.14

éĪ

0.14

ylvania

0.14

ãģĵãģĿ

0.14

iÅ¡tÄĽ

0.14

 enumerator

0.14

PEAT

0.14

serde

0.13

Ú¯Ø²

0.13

Aim

0.13

Activations Density 0.058%

phrases related to significant events or changes in policy and governance

No Comments

No Known Activations