INDEX

Explanations

terms and phrases associated with the concept of normality across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uyu

-0.16

eling

-0.15

lbrace

-0.15

qli

-0.14

_CONNECTED

-0.14

 autor

-0.14

usp

-0.14

aurus

-0.14

undry

-0.14

omic

-0.14

POSITIVE LOGITS

uds

0.17

strup

0.16

pio

0.16

 disp

0.15

atab

0.15

ity

0.14

mente

0.14

adder

0.14

alty

0.14

atch

0.14

Activations Density 0.039%

terms and phrases associated with the concept of normality across various contexts

No Comments

No Known Activations