INDEX

Explanations

entities related to organizations, institutions, and people involved in governance and community activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

à¸µà¸Ķ

-0.16

erson

-0.15

IODevice

-0.15

SSIP

-0.15

_marshall

-0.15

.usermodel

-0.14

agli

-0.14

quete

-0.14

Cpp

-0.14

conciliation

-0.14

POSITIVE LOGITS

 became

0.18

 suddenly

0.17

 began

0.17

 rings

0.16

 summ

0.16

 begin

0.16

0.15

 Rings

0.15

 came

0.15

.Begin

0.15

Activations Density 0.159%

entities related to organizations, institutions, and people involved in governance and community activities

No Comments

No Known Activations