INDEX

Explanations

mentions of language learning platforms and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uur

-0.15

.heroku

-0.15

inn

-0.15

irate

-0.15

&view

-0.15

-0.14

 Pattern

-0.14

adora

-0.14

ackets

-0.14

Ð±Ð°Ð²

-0.13

POSITIVE LOGITS

sian

0.15

 extents

0.14

ahy

0.14

ãĥĥãĥģ

0.14

umbed

0.14

boxed

0.14

VRT

0.14

Hub

0.13

hash

0.13

jp

0.13

Activations Density 0.023%

mentions of language learning platforms and their features

No Comments

No Known Activations