INDEX

Explanations

references to geographical locations and their associated attributes

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

ipo

-0.16

uman

-0.15

illard

-0.14

åĽ£

-0.14

 foreign

-0.14

EGIN

-0.14

 Foreign

-0.14

.circular

-0.14

ë§Ŀ

-0.14

azzi

-0.13

POSITIVE LOGITS

auga

0.17

olan

0.17

-wide

0.17

olor

0.16

ahir

0.16

 ãģĿãģ®ä»ĸ

0.16

vla

0.15

.od

0.14

ÏĦÏĥ

0.14

Od

0.14

Activations Density 0.225%

references to geographical locations and their associated attributes

No Comments

No Known Activations