INDEX

Explanations

phrases related to the approval of certain actions or decisions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

alet

-0.15

ipherals

-0.14

 Meer

-0.14

alam

-0.14

igu

-0.14

 Gate

-0.13

 gates

-0.13

 gate

-0.13

POSITIVE LOGITS

 pylint

0.16

 phÃ³ng

0.16

 CreateMap

0.15

ä»½

0.15

specs

0.14

ä¼Ļ

0.14

noinspection

0.13

MouseButton

0.13

istes

0.13

 ApiController

0.13

Activations Density 0.111%

phrases related to the approval of certain actions or decisions

No Comments

No Known Activations