INDEX

Explanations

terms and references related to barriers and fencing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 baiser

-0.17

andom

-0.16

ylland

-0.15

áº¾

-0.15

liner

-0.15

readcr

-0.15

Ä±rak

-0.14

ÂłÐ¼

-0.14

.rs

-0.14

 Scandin

-0.14

POSITIVE LOGITS

net

0.19

Net

0.14

odie

0.14

mur

0.14

ows

0.14

ilians

0.14

lew

0.13

los

0.13

Activations Density 0.033%

terms and references related to barriers and fencing

No Comments

No Known Activations