INDEX

Explanations

terms related to software features and functionalities

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

-0.15

ilo

-0.14

akens

-0.14

oven

-0.14

äºĮäºº

-0.14

Pur

-0.14

pir

-0.14

 twist

-0.13

olio

-0.13

POSITIVE LOGITS

isini

0.15

icros

0.15

ller

0.14

äºľ

0.14

licant

0.14

Ð¿ÑĢ

0.14

 Percy

0.14

 Kane

0.13

ssa

0.13

erras

0.13

Activations Density 0.610%

terms related to software features and functionalities

No Comments

No Known Activations