INDEX

Explanations

phrases related to academic research and statistical methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ICAST

-0.16

.executeQuery

-0.16

ahoo

-0.15

idlo

-0.14

 subrange

-0.14

kul

-0.14

 Loose

-0.14

 porr

-0.14

-figure

-0.14

 Hind

-0.14

POSITIVE LOGITS

 censor

0.23

eter

0.19

 Survival

0.17

 Observation

0.17

 survival

0.16

 hazards

0.15

cov

0.15

SAS

0.15

 Treatment

0.15

Activations Density 0.027%

phrases related to academic research and statistical methods

No Comments

No Known Activations