INDEX

Explanations

phrases related to ongoing processes and improvements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

omo

-0.16

ews

-0.15

ä»ĭ

-0.15

-0.14

[of

-0.14

egasus

-0.13

POSITIVE LOGITS

 simultaneously

0.20

doch

0.15

ctal

0.15

 zÃ¡roveÅĪ

0.15

ãĥ³ãĥĳ

0.15

 ALSO

0.14

 simult

0.14

ritch

0.14

ãĥ³ãĤº

0.14

 concurrently

0.14

Activations Density 0.122%

phrases related to ongoing processes and improvements

No Comments

No Known Activations