INDEX

Explanations

references to technical or programming concepts, particularly related to data handling and processing functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Garland

-0.15

SSION

-0.14

 Repos

-0.13

 slash

-0.13

muz

-0.13

kel

-0.13

 Stad

-0.13

ons

-0.13

 public

-0.13

POSITIVE LOGITS

ponde

0.16

ijo

0.15

 gerek

0.15

ufs

0.14

ec

0.14

undred

0.14

ecast

0.14

omic

0.13

SA

0.13

opia

0.13

Activations Density 0.097%

references to technical or programming concepts, particularly related to data handling and processing functions

No Comments

No Known Activations