INDEX

Explanations

references to educational institutions and notable individuals in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

nej

-0.17

clair

-0.16

cheid

-0.15

 Auch

-0.15

chn

-0.15

_MAC

-0.15

orida

-0.15

angi

-0.15

_dashboard

-0.15

readcr

-0.14

POSITIVE LOGITS

 Germany

0.17

nat

0.17

unya

0.17

 German

0.16

 german

0.16

ipsis

0.16

German

0.15

åľ³

0.15

Germany

0.15

Activations Density 0.644%

references to educational institutions and notable individuals in academic contexts

No Comments

No Known Activations