INDEX

Explanations

elements related to specific geographical or administrative locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

afone

-0.17

.bb

-0.17

loff

-0.16

emouth

-0.16

ableViewController

-0.16

ÙĪÙĦÙĬ

-0.16

lian

-0.16

 GLOBAL

-0.16

igon

-0.15

lehem

-0.15

POSITIVE LOGITS

most

0.19

ward

0.17

ìª½

0.17

wards

0.17

vg

0.16

0.15

-most

0.15

 compact

0.15

argas

0.14

 Compact

0.14

Activations Density 0.093%

elements related to specific geographical or administrative locations

No Comments

No Known Activations