INDEX

Explanations

negations and expressions of uncertainty or non-affirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ãĥ©ãĥ¼

-0.14

zech

-0.14

apis

-0.14

 sacr

-0.14

 hang

-0.14

rink

-0.13

plies

-0.13

 Kane

-0.13

Wie

-0.13

tel

-0.13

POSITIVE LOGITS

ubbo

0.15

ãģ£ãģ¡

0.15

ystone

0.15

åħ·

0.14

AutoSize

0.14

 Milit

0.14

auss

0.14

ÄŁu

0.14

ebin

0.14

ubat

0.14

Activations Density 0.107%

negations and expressions of uncertainty or non-affirmation

No Comments

No Known Activations