INDEX

Explanations

references to entertainment or media terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icy

-0.16

 Belg

-0.14

Persist

-0.14

Ire

-0.14

 Birch

-0.14

ksi

-0.13

 sourceMapping

-0.13

 rein

-0.13

quate

-0.13

 setC

-0.13

POSITIVE LOGITS

0.15

preter

0.15

Duy

0.14

 bohat

0.14

 Flag

0.13

enton

0.13

enko

0.13

zon

0.13

pike

0.13

 yÄ±lda

0.13

Activations Density 11.519%

references to entertainment or media terminology

No Comments

No Known Activations