INDEX

Explanations

references to individuals, particularly in the context of notable figures or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

utar

-0.17

uden

-0.14

ãģ¡ãĤĥãĤĵ

-0.14

otate

-0.14

 bdsm

-0.14

ãĥ¼ãĥ¼

-0.14

antan

-0.14

Degrees

-0.14

maal

-0.14

isson

-0.13

POSITIVE LOGITS

.dtd

0.16

ypse

0.15

.dk

0.14

0.13

um

0.13

 variant

0.13

orda

0.13

 Cove

0.13

 Walt

0.13

Squ

0.13

Activations Density 0.536%

references to individuals, particularly in the context of notable figures or events

No Comments

No Known Activations