INDEX

Explanations

references to a specific individual or entity, particularly focusing on name variations and possessive forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ingly

-0.16

omed

-0.16

ra

-0.16

usz

-0.15

ledge

-0.15

bearer

-0.14

è´§

-0.14

resse

-0.14

nya

-0.14

ÑĬ

-0.14

POSITIVE LOGITS

bst

0.23

itage

0.22

editary

0.20

usalem

0.19

metic

0.19

encia

0.18

 Majesty

0.18

amient

0.17

asmus

0.17

ding

0.16

Activations Density 0.036%

references to a specific individual or entity, particularly focusing on name variations and possessive forms

No Comments

No Known Activations