INDEX

Explanations

references to the name "Rit" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

cratch

-0.17

chalk

-0.16

erif

-0.16

adata

-0.15

lec

-0.15

idge

-0.15

IPA

-0.15

iac

-0.15

erule

-0.15

iji

-0.14

POSITIVE LOGITS

ual

0.24

ually

0.21

UAL

0.20

uality

0.20

chie

0.18

gers

0.17

wik

0.16

anic

0.15

tier

0.15

adel

0.15

Activations Density 0.011%

references to the name "Rit" and its variations in various contexts

No Comments

No Known Activations