INDEX

Explanations

programming and user interaction events within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

istine

-0.18

kel

-0.18

curso

-0.16

bsolute

-0.15

caz

-0.15

chyb

-0.15

alog

-0.14

ãĥ¼ãĥĪ

-0.14

omy

-0.14

ÐµÑģÑĤ

-0.14

POSITIVE LOGITS

mdb

0.16

 Seamless

0.15

eda

0.14

 vent

0.14

raph

0.14

ero

0.14

 triggers

0.14

(show

0.14

0.13

NR

0.13

Activations Density 0.137%

programming and user interaction events within a technical context

No Comments

No Known Activations