INDEX

Explanations

proper nouns related to individuals, places, and events

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

ãĥ¼ãĥį

-0.15

ÐĶÐļ

-0.14

OrNull

-0.14

.freeze

-0.14

zin

-0.14

uve

-0.13

nist

-0.13

anz

-0.13

 pÅĻÃŃpadnÄĽ

-0.13

inand

-0.13

POSITIVE LOGITS

0.23

–

0.19

0.18

Pt

0.17

pt

0.15

aka

0.15

vs

0.15

 interview

0.14

(~

0.14

Activations Density 0.132%

proper nouns related to individuals, places, and events

No Comments

No Known Activations