INDEX

Explanations

phrases indicating actions, intentions, or states of being

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

ì¸¡

-0.14

/Library

-0.14

ruba

-0.13

uner

-0.13

UpDown

-0.13

iances

-0.13

evin

-0.13

riv

-0.13

.DataVisualization

-0.13

 investigators

-0.12

POSITIVE LOGITS

opsis

0.17

utzer

0.16

 Eigen

0.15

Fo

0.15

ffer

0.15

 Wass

0.14

 Baum

0.14

eya

0.14

rogen

0.14

erus

0.14

Activations Density 0.367%

phrases indicating actions, intentions, or states of being

No Comments

No Known Activations