INDEX

Explanations

phrases related to actions and decision-making 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

adlo

-0.16

andler

-0.15

 Clarkson

-0.15

èĿ

-0.15

 addCriterion

-0.15

anou

-0.14

finder

-0.14

mac

-0.14

anko

-0.14

eline

-0.13

POSITIVE LOGITS

 cater

0.15

.Override

0.15

 catering

0.14

 Trot

0.14

oux

0.14

ikh

0.14

.addObserver

0.14

><?

0.14

 abstract

0.14

coni

0.14

Activations Density 0.144%

phrases related to actions and decision-making in various contexts

No Comments

No Known Activations