INDEX

Explanations

comparative phrases indicating proportions or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ught

-0.16

orate

-0.16

-0.15

 nues

-0.15

onas

-0.14

luet

-0.14

ICLE

-0.14

 cazzo

-0.14

iman

-0.14

shint

-0.14

POSITIVE LOGITS

 portion

0.16

 portions

0.15

abet

0.15

 majority

0.15

 thousands

0.15

 Majority

0.15

ãģ®ãģ¯

0.14

ubat

0.14

anio

0.14

ucer

0.14

Activations Density 0.065%

comparative phrases indicating proportions or quantities

No Comments

No Known Activations