INDEX

Explanations

prepositions indicating context or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ogne

-0.15

 Avery

-0.15

Ã³mo

-0.15

front

-0.14

ocker

-0.14

Sty

-0.13

adia

-0.13

ares

-0.13

-front

-0.13

Eh

-0.13

POSITIVE LOGITS

ARGER

0.15

azon

0.14

RYPT

0.13

hled

0.13

ForObject

0.13

Ø³ØªØ±

0.13

ãĥĸãĥª

0.13

CustomLabel

0.13

ÑĩÐ¸Ð½

0.13

Activations Density 0.158%

prepositions indicating context or location

No Comments

No Known Activations