INDEX

Explanations

names of historical figures and locations associated with various geopolitical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

itas

-0.18

Äįka

-0.15

åı

-0.15

 fronts

-0.14

-navigation

-0.14

Gut

-0.14

estro

-0.13

ı

-0.13

 indeb

-0.13

å§ĭ

-0.13

POSITIVE LOGITS

ansen

0.16

IfExists

0.15

oyer

0.14

 Britt

0.14

unlock

0.14

Ø§ÙĦÙĩ

0.14

ł

0.13

 linh

0.13

SB

0.13

atorium

0.13

Activations Density 1.167%

names of historical figures and locations associated with various geopolitical events

No Comments

No Known Activations