INDEX

Explanations

topics related to debates and discussions about societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

zhou

-0.14

Ã©al

-0.14

ops

-0.14

ÐµÐ²Ð¸Ñĩ

-0.13

eÄį

-0.13

_typ

-0.13

 Jiang

-0.13

 BOTTOM

-0.13

 Toolbox

-0.12

ãĥįãĥ«

-0.12

POSITIVE LOGITS

utex

0.17

izontal

0.14

.ie

0.13

Los

0.13

 QModelIndex

0.13

.fi

0.13

uchs

0.13

ãģ°ãģĭãĤĬ

0.13

ssi

0.13

caffold

0.13

Activations Density 0.094%

topics related to debates and discussions about societal issues

No Comments

No Known Activations