INDEX

Explanations

words related to names or people, with a focus on familial or relational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

stile

-0.17

infeld

-0.16

Porno

-0.15

èĬ¸

-0.15

ØªÙĬÙĨ

-0.15

eenth

-0.15

çŃĨ

-0.15

angelo

-0.15

.getOwnProperty

-0.15

ëĿ¼ëıĦ

-0.14

POSITIVE LOGITS

etta

0.18

throp

0.17

ipur

0.16

ferred

0.15

ystate

0.15

cif

0.15

lia

0.15

 Mattis

0.14

hattan

0.14

Activations Density 0.088%

words related to names or people, with a focus on familial or relational contexts

No Comments

No Known Activations