INDEX

Explanations

references to historical events and figures, particularly those associated with conflicts or significant legal rulings

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

ATUS

-0.16

 Coleman

-0.14

à¹Ģà¸ķ

-0.14

rÃ¥

-0.14

 strictly

-0.14

aving

-0.14

uencia

-0.14

lili

-0.13

nah

-0.13

 Freund

-0.13

POSITIVE LOGITS

 swallow

0.18

chor

0.16

ibir

0.15

stor

0.15

å¿ľ

0.14

ariate

0.14

ijn

0.14

ophone

0.14

ãģıãģł

0.13

HAL

0.13

Activations Density 0.439%

references to historical events and figures, particularly those associated with conflicts or significant legal rulings

No Comments

No Known Activations