INDEX

Explanations

instances of ongoing activities and their connections to locations or contexts in narratives

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

-0.17

ele

-0.15

riot

-0.15

nia

-0.15

ANGER

-0.14

bd

-0.14

zzo

-0.14

aus

-0.14

endoza

-0.14

igr

-0.14

POSITIVE LOGITS

ideos

0.16

Ã©ment

0.16

QRST

0.15

oeff

0.15

SWG

0.15

Ãłn

0.15

ãģĹãĤĩ

0.15

ãģıãĤĵ

0.14

VOKE

0.14

Activations Density 0.022%

instances of ongoing activities and their connections to locations or contexts in narratives

No Comments

No Known Activations