INDEX

Explanations

occurrences of the term "on" in 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

addir

-0.15

iciÃ³n

-0.15

achten

-0.15

defaults

-0.14

cly

-0.14

 eben

-0.14

alm

-0.14

amik

-0.14

alem

-0.14

ahoo

-0.13

POSITIVE LOGITS

 disc

0.17

ÑĢÐ¸Ðº

0.16

ews

0.16

ÄĻd

0.15

ilogue

0.15

/off

0.15

ocs

0.15

ICES

0.15

 Mueller

0.14

.vertx

0.14

Activations Density 0.076%

occurrences of the term "on" in various contexts

No Comments

No Known Activations