INDEX

Explanations

possessive forms indicating ownership or affiliation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

enheim

-0.17

lier

-0.16

GLOBALS

-0.14

[Math

-0.14

ediator

-0.14

urs

-0.14

Å¯

-0.13

Kou

-0.13

POSITIVE LOGITS

 economy

0.21

stre

0.15

phinx

0.15

 public

0.14

 Past

0.14

ÃĸL

0.14

 Economy

0.14

 Lump

0.14

 culture

0.14

ÅĻi

0.14

Activations Density 0.082%

possessive forms indicating ownership or affiliation

No Comments

No Known Activations