INDEX

Explanations

phrases related to modeling and analysis techniques in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

radient

-0.17

 marginal

-0.16

 stren

-0.16

:CGRect

-0.15

 multin

-0.15

 margin

-0.14

 Rubin

-0.14

åĭ

-0.14

ÅĽÄĩ

-0.14

allel

-0.14

POSITIVE LOGITS

Ø§ØŃ

0.17

ocks

0.15

 ########.

0.14

pekt

0.14

å¸Ī

0.14

hdl

0.14

enor

0.13

å¸«

0.13

Activations Density 0.014%

phrases related to modeling and analysis techniques in various contexts

No Comments

No Known Activations