INDEX

Explanations

possessive forms of nouns

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

arness

-0.19

dre

-0.16

hin

-0.15

ange

-0.15

utow

-0.15

etting

-0.15

nex

-0.15

oca

-0.15

thalm

-0.14

wm

-0.14

POSITIVE LOGITS

wide

0.16

lef

0.15

Wide

0.14

ê°Ħ

0.14

iversit

0.14

 Ð´Ð¾ÑĤ

0.13

_own

0.13

 Wide

0.13

-wide

0.13

 ActiveSupport

0.13

Activations Density 0.068%

possessive forms of nouns

No Comments

No Known Activations