INDEX

Explanations

instances of numerical data or quantitative information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

odi

-0.16

 fisse

-0.14

orage

-0.14

etten

-0.14

itech

-0.14

Ã¤Ã¤n

-0.14

 Hogan

-0.13

annah

-0.13

iro

-0.13

POSITIVE LOGITS

AGENT

0.14

wrapper

0.14

/apt

0.14

ÏĮÎ½

0.14

_reporting

0.14

gio

0.14

ziej

0.13

æ´ģ

0.13

erna

0.13

isle

0.13

Activations Density 0.031%

instances of numerical data or quantitative information

No Comments

No Known Activations