INDEX

Explanations

punctuation and formatting indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Implementation

-0.17

Configuration

-0.16

Parameters

-0.15

SupportedContent

-0.14

Existing

-0.14

Develop

-0.14

Initialization

-0.13

Specification

-0.13

PostalCodes

-0.13

Processes

-0.13

POSITIVE LOGITS

played

0.22

Jake

0.22

nee

0.21

Danny

0.20

Jamie

0.20

aka

0.20

Aaron

0.20

Sean

0.20

Kyle

0.20

Neal

0.20

Activations Density 0.157%

punctuation and formatting indicators

No Comments

No Known Activations