INDEX

Explanations

project-related terms and identifiers in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lass

-0.17

ensis

-0.15

obl

-0.14

ersive

-0.14

icle

-0.14

arp

-0.14

 Bott

-0.14

 Father

-0.14

ÐµÑĪ

-0.14

rum

-0.13

POSITIVE LOGITS

WithOptions

0.16

ieux

0.15

ãģĻãģĻ

0.15

à¤¦à¤°

0.15

 Hicks

0.14

SSP

0.14

Ð¿Ð¾Ð²

0.14

sWith

0.13

OKIE

0.13

Activations Density 0.032%

project-related terms and identifiers in a structured format

No Comments

No Known Activations