INDEX

Explanations

roles and titles associated with professions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ð»Ð°Ð´Ð¸

-0.17

 bott

-0.16

?key

-0.16

cheid

-0.16

ryo

-0.16

ê³¡

-0.15

ÑĸÑĹÐ²

-0.15

Serialized

-0.14

Ã©ric

-0.14

.cgi

-0.14

POSITIVE LOGITS

 shim

0.15

anki

0.14

 Campo

0.14

clus

0.14

Hall

0.14

-NLS

0.14

 Simpson

0.13

 Press

0.13

oe

0.13

Åº

0.13

Activations Density 0.855%

roles and titles associated with professions

No Comments

No Known Activations