INDEX

Explanations

terms related to academic publishing and research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 hypert

-0.14

vin

-0.14

 Newspaper

-0.14

çĥŁ

-0.14

Åº

-0.14

zos

-0.14

Occurrences

-0.14

 smoke

-0.13

å¤ªéĥİ

-0.13

achu

-0.13

POSITIVE LOGITS

 widest

0.19

 contributions

0.17

 contributed

0.16

mgr

0.16

acam

0.15

ÑıÑĩ

0.15

contrib

0.15

éº»

0.15

chaft

0.14

 Contrib

0.14

Activations Density 0.020%

terms related to academic publishing and research

No Comments

No Known Activations