INDEX

Explanations

phrases that indicate the actions and characteristics of individuals 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ucene

-0.15

astle

-0.14

onde

-0.14

 é©

-0.13

oksen

-0.13

ulus

-0.13

vale

-0.13

rrha

-0.13

apse

-0.13

POSITIVE LOGITS

ÑĩÐµ

0.17

0.14

 prem

0.14

 dÃ©jÃł

0.14

ought

0.14

ABS

0.14

ADB

0.14

 repeatedly

0.14

ENTA

0.14

rou

0.13

Activations Density 0.122%

phrases that indicate the actions and characteristics of individuals in various contexts

No Comments

No Known Activations