INDEX

Explanations

occurrences of the names and designations related to a specific educational institution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ãģ¤ãģ¶

-0.15

illes

-0.14

acic

-0.14

;display

-0.14

abay

-0.14

Æ

-0.13

Î²Î¿Î»

-0.13

agu

-0.13

azzo

-0.13

eken

-0.13

POSITIVE LOGITS

Le

0.18

oldt

0.16

(le

0.16

frog

0.15

le

0.15

nict

0.15

hana

0.15

inton

0.15

ington

0.15

hardt

0.14

Activations Density 0.045%

occurrences of the names and designations related to a specific educational institution

No Comments

No Known Activations