INDEX

Explanations

specific names and titles, often related to individuals or organizations

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

ÑĮÐºÐ¾

-0.15

uckle

-0.15

porto

-0.14

ãĤ¯ãĥ©ãĥĸ

-0.14

ÐµÐ²ÐµÑĢ

-0.14

PÅĻi

-0.14

acher

-0.13

(TM

-0.13

Äįit

-0.13

 Ð¿Ð¾Ð½

-0.13

POSITIVE LOGITS

alars

0.17

Sco

0.15

edm

0.15

endors

0.14

oi

0.14

ifting

0.13

 Ä°st

0.13

ãģŁãģĦ

0.13

anka

0.13

Wo

0.13

Activations Density 0.119%

specific names and titles, often related to individuals or organizations

No Comments

No Known Activations