INDEX

Explanations

specific numerical values and references related to time and location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

DS

-0.17

SSF

-0.16

-0.14

Ø§Ø·

-0.14

 Pear

-0.14

 =↵

-0.14

 property

-0.14

 Poetry

-0.13

á»©

-0.13

anza

-0.13

POSITIVE LOGITS

combe

0.16

culo

0.16

zin

0.16

onte

0.15

rians

0.14

verbs

0.14

urum

0.14

ä¸įçŁ¥

0.14

Î³ÎºÎ±

0.14

ceptar

0.14

Activations Density 0.261%

specific numerical values and references related to time and location

No Comments

No Known Activations