INDEX

Explanations

phrases related to the presence or involvement of an item or element in a context

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

 Marino

-0.15

urile

-0.15

asics

-0.15

-REAL

-0.15

ACES

-0.15

à¤Ľ

-0.15

acier

-0.14

èµĸ

-0.14

ModelProperty

-0.14

otty

-0.14

POSITIVE LOGITS

éĺª

0.15

.TabStop

0.15

uzzi

0.15

eriod

0.14

 oppos

0.14

IDO

0.14

ekk

0.14

oley

0.14

èĽĽ

0.13

à¸Ńà¸ĩà¸Īà¸²à¸ģ

0.13

Activations Density 0.015%

phrases related to the presence or involvement of an item or element in a context

No Comments

No Known Activations