INDEX

Explanations

numerical data and versioning information related to software and applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ledik

-0.17

åĨĨ

-0.15

ibern

-0.15

apus

-0.15

-0.14

avis

-0.14

ecided

-0.14

ournals

-0.14

Reuse

-0.14

alez

-0.14

POSITIVE LOGITS

_RC

0.15

 Thousand

0.14

enery

0.14

 development

0.13

ization

0.13

hs

0.13

 Â¿

0.13

elist

0.13

shan

0.13

errs

0.13

Activations Density 0.030%

numerical data and versioning information related to software and applications

No Comments

No Known Activations