INDEX

Explanations

questions and queries about consumer experiences and product offerings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Darling

-0.16

Bab

-0.16

nos

-0.15

iedo

-0.14

afari

-0.14

_cookie

-0.14

 sooner

-0.14

áº§u

-0.14

-0.13

POSITIVE LOGITS

EMPLARY

0.17

Ã¡v

0.15

fds

0.15

 Yates

0.15

pom

0.14

enant

0.14

MMC

0.14

Ã¦kke

0.14

asse

0.14

safe

0.13

Activations Density 0.973%

questions and queries about consumer experiences and product offerings

No Comments

No Known Activations