INDEX

Explanations

references to picnics

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

-0.15

baugh

-0.15

itude

-0.15

ephy

-0.14

isode

-0.14

ãģ¤ãģ¶

-0.14

ãģĹãģ¦ãĤĤ

-0.14

 Pascal

-0.14

endars

-0.14

POSITIVE LOGITS

rosse

0.15

 Hurt

0.15

ee

0.15

QL

0.14

IEL

0.14

iol

0.14

arium

0.14

 Marian

0.13

iel

0.13

åĮº

0.13

Activations Density 0.004%

references to picnics

No Comments

No Known Activations