INDEX

Explanations

terms related to various types of services and products

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

loo

-0.15

emos

-0.15

Criterion

-0.15

Contours

-0.15

ÙĪÙĬØ©

-0.15

Î¼Î¹Î¿

-0.14

éº¦

-0.14

Sez

-0.14

 fscanf

-0.14

PerPixel

-0.14

POSITIVE LOGITS

Ð¾Ð±Ð¾Ð²

0.18

hr

0.15

chl

0.15

iesta

0.15

 Hass

0.15

Î´Î·

0.14

atch

0.14

illon

0.14

ictions

0.14

 ç¾

0.14

Activations Density 0.006%

terms related to various types of services and products

No Comments

No Known Activations