INDEX

Explanations

comments and documentation related to code implementation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

inke

-0.17

nard

-0.16

rieg

-0.16

 avan

-0.16

rouch

-0.15

.managed

-0.14

(Encoding

-0.14

ysi

-0.14

ilog

-0.14

asics

-0.14

POSITIVE LOGITS

à¸Ļà¸²à¸¡

0.15

Hv

0.15

ategorized

0.14

.Requires

0.14

.stamp

0.13

astics

0.13

leared

0.13

flow

0.13

ãĥīãĥ«

0.13

å§«

0.13

Activations Density 0.004%

comments and documentation related to code implementation

No Comments

No Known Activations