INDEX

Explanations

inquiries and references related to questioning and seeking information from others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

edin

-0.17

iedo

-0.16

neau

-0.15

imers

-0.15

 pied

-0.14

inky

-0.14

erland

-0.14

rium

-0.14

iegel

-0.14

 èī¯

-0.14

POSITIVE LOGITS

EventArgs

0.15

boru

0.14

 shar

0.14

EventHandler

0.14

version

0.14

reator

0.14

 despre

0.14

Ð°ÑĢÑħ

0.13

 condom

0.13

åĽ

0.13

Activations Density 0.192%

inquiries and references related to questioning and seeking information from others

No Comments

No Known Activations