INDEX

Explanations

words or phrases involving the concept of belonging or membership within a group or entity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

èĹ

-0.17

 Kraj

-0.17

apur

-0.15

 há»ĵi

-0.15

iza

-0.14

inch

-0.14

ses

-0.14

ille

-0.13

UES

-0.13

orro

-0.13

POSITIVE LOGITS

0.16

ÐµÑĦ

0.14

enie

0.14

eward

0.14

WARDED

0.14

ceae

0.14

éª¨

0.14

mdb

0.13

 elÃ©

0.13

Activations Density 0.030%

words or phrases involving the concept of belonging or membership within a group or entity

No Comments

No Known Activations