INDEX

Explanations

references to dates and months, particularly related to historical events or records

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Joel

-0.15

dag

-0.15

ummer

-0.14

atre

-0.14

ench

-0.13

 :↵

-0.13

Å¥

-0.13

ustum

-0.13

cow

-0.13

aleigh

-0.13

POSITIVE LOGITS

INGTON

0.15

nodoc

0.15

/vnd

0.14

ington

0.14

 SelectListItem

0.14

kelig

0.14

uez

0.13

ily

0.13

 columnIndex

0.13

ewood

0.13

Activations Density 0.011%

references to dates and months, particularly related to historical events or records

No Comments

No Known Activations