INDEX

Explanations

references to authorship and the act of writing

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

ew

-0.17

arts

-0.15

ayers

-0.15

Rak

-0.15

ey

-0.15

-eyed

-0.15

Î²Î¬

-0.15

eners

-0.15

-haired

-0.15

Ø§ØªÛĮ

-0.15

POSITIVE LOGITS

ship

0.20

UPPORTED

0.17

itative

0.16

YSTEM

0.16

lient

0.16

ifold

0.15

rego

0.15

ignum

0.15

upported

0.14

ifice

0.14

Activations Density 0.027%

references to authorship and the act of writing

No Comments

No Known Activations