INDEX

Explanations

concepts related to qualities and states, especially those ending in '-ity'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ysz

-0.17

sv

-0.16

sql

-0.15

 EÅŁ

-0.15

owie

-0.15

ings

-0.14

out

-0.14

ingu

-0.14

ÑĥÑĩ

-0.13

ugi

-0.13

POSITIVE LOGITS

ously

0.16

esterday

0.15

estar

0.15

gger

0.15

-minded

0.15

andex

0.15

 quot

0.14

eus

0.14

eon

0.14

 gros

0.13

Activations Density 0.394%

concepts related to qualities and states, especially those ending in '-ity'

No Comments

No Known Activations