INDEX

Explanations

mentions of the word "Roland" and its variants 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 @ 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

kill

-0.15

ekil

-0.14

iversit

-0.14

 VÃ¡c

-0.14

.synthetic

-0.14

 Sous

-0.14

ãĥĨãĥ«

-0.14

.mc

-0.13

 ones

-0.13

ãĤĮ

-0.13

POSITIVE LOGITS

stÃŃ

0.15

vo

0.15

ertas

0.14

 RedirectTo

0.14

adia

0.14

ULA

0.14

mium

0.14

Î²Îµ

0.14

erville

0.14

Ã¹ng

0.14

Activations Density 0.005%

mentions of the word "Roland" and its variants in various contexts

No Comments

No Known Activations